From f382fc0ecfb67744118a3f8de0a928f38586c42b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:56 -0700 Subject: [PATCH 001/162] fscrypt: fix all kerneldoc warnings Fix all kerneldoc warnings in fs/crypto/ and include/linux/fscrypt.h. Most of these were due to missing documentation for function parameters. Detected with: scripts/kernel-doc -v -none fs/crypto/*.{c,h} include/linux/fscrypt.h This cleanup makes it possible to check new patches for kerneldoc warnings without having to filter out all the existing ones. For consistency, also adjust some function "brief descriptions" to include the parentheses and to wrap at 80 characters. (The latter matches the checkpatch expectation.) Link: https://lore.kernel.org/r/20200511191358.53096-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/crypto/crypto.c | 9 +++++-- fs/crypto/fname.c | 52 +++++++++++++++++++++++++++---------- fs/crypto/fscrypt_private.h | 4 +-- fs/crypto/hooks.c | 4 +-- fs/crypto/keysetup.c | 9 ++++--- fs/crypto/policy.c | 19 +++++++++++--- include/linux/fscrypt.h | 19 +++++++++----- 7 files changed, 82 insertions(+), 34 deletions(-) diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index dcbd507824b7..e56da1d6b2e7 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -53,6 +53,7 @@ struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags) /** * fscrypt_free_bounce_page() - free a ciphertext bounce page + * @bounce_page: the bounce page to free, or NULL * * Free a bounce page that was allocated by fscrypt_encrypt_pagecache_blocks(), * or by fscrypt_alloc_bounce_page() directly. @@ -131,7 +132,8 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, } /** - * fscrypt_encrypt_pagecache_blocks() - Encrypt filesystem blocks from a pagecache page + * fscrypt_encrypt_pagecache_blocks() - Encrypt filesystem blocks from a + * pagecache page * @page: The locked pagecache page containing the block(s) to encrypt * @len: Total size of the block(s) to encrypt. Must be a nonzero * multiple of the filesystem's block size. @@ -221,7 +223,8 @@ int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, EXPORT_SYMBOL(fscrypt_encrypt_block_inplace); /** - * fscrypt_decrypt_pagecache_blocks() - Decrypt filesystem blocks in a pagecache page + * fscrypt_decrypt_pagecache_blocks() - Decrypt filesystem blocks in a + * pagecache page * @page: The locked pagecache page containing the block(s) to decrypt * @len: Total size of the block(s) to decrypt. Must be a nonzero * multiple of the filesystem's block size. @@ -345,6 +348,8 @@ void fscrypt_msg(const struct inode *inode, const char *level, /** * fscrypt_init() - Set up for fs encryption. + * + * Return: 0 on success; -errno on failure */ static int __init fscrypt_init(void) { diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 5db3cc8c07e3..5e0c24415583 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -18,7 +18,7 @@ #include #include "fscrypt_private.h" -/** +/* * struct fscrypt_nokey_name - identifier for directory entry when key is absent * * When userspace lists an encrypted directory without access to the key, the @@ -106,9 +106,12 @@ static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) /** * fscrypt_fname_encrypt() - encrypt a filename - * - * The output buffer must be at least as large as the input buffer. - * Any extra space is filled with NUL padding before encryption. + * @inode: inode of the parent directory (for regular filenames) + * or of the symlink (for symlink targets) + * @iname: the filename to encrypt + * @out: (output) the encrypted filename + * @olen: size of the encrypted filename. It must be at least @iname->len. + * Any extra space is filled with NUL padding before encryption. * * Return: 0 on success, -errno on failure */ @@ -158,8 +161,11 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, /** * fname_decrypt() - decrypt a filename - * - * The caller must have allocated sufficient memory for the @oname string. + * @inode: inode of the parent directory (for regular filenames) + * or of the symlink (for symlink targets) + * @iname: the encrypted filename to decrypt + * @oname: (output) the decrypted filename. The caller must have allocated + * enough space for this, e.g. using fscrypt_fname_alloc_buffer(). * * Return: 0 on success, -errno on failure */ @@ -207,7 +213,10 @@ static const char lookup_table[65] = #define BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3) /** - * base64_encode() - + * base64_encode() - base64-encode some bytes + * @src: the bytes to encode + * @len: number of bytes to encode + * @dst: (output) the base64-encoded string. Not NUL-terminated. * * Encodes the input string using characters from the set [A-Za-z0-9+,]. * The encoded string is roughly 4/3 times the size of the input string. @@ -273,7 +282,12 @@ bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len, } /** - * fscrypt_fname_alloc_buffer - allocate a buffer for presented filenames + * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames + * @inode: inode of the parent directory (for regular filenames) + * or of the symlink (for symlink targets) + * @max_encrypted_len: maximum length of encrypted filenames the buffer will be + * used to present + * @crypto_str: (output) buffer to allocate * * Allocate a buffer that is large enough to hold any decrypted or encoded * filename (null-terminated), for the given maximum encrypted filename length. @@ -298,9 +312,10 @@ int fscrypt_fname_alloc_buffer(const struct inode *inode, EXPORT_SYMBOL(fscrypt_fname_alloc_buffer); /** - * fscrypt_fname_free_buffer - free the buffer for presented filenames + * fscrypt_fname_free_buffer() - free a buffer for presented filenames + * @crypto_str: the buffer to free * - * Free the buffer allocated by fscrypt_fname_alloc_buffer(). + * Free a buffer that was allocated by fscrypt_fname_alloc_buffer(). */ void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) { @@ -312,10 +327,19 @@ void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) EXPORT_SYMBOL(fscrypt_fname_free_buffer); /** - * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user - * space - * - * The caller must have allocated sufficient memory for the @oname string. + * fscrypt_fname_disk_to_usr() - convert an encrypted filename to + * user-presentable form + * @inode: inode of the parent directory (for regular filenames) + * or of the symlink (for symlink targets) + * @hash: first part of the name's dirhash, if applicable. This only needs to + * be provided if the filename is located in an indexed directory whose + * encryption key may be unavailable. Not needed for symlink targets. + * @minor_hash: second part of the name's dirhash, if applicable + * @iname: encrypted filename to convert. May also be "." or "..", which + * aren't actually encrypted. + * @oname: output buffer for the user-presentable filename. The caller must + * have allocated enough space for this, e.g. using + * fscrypt_fname_alloc_buffer(). * * If the key is available, we'll decrypt the disk name. Otherwise, we'll * encode it for presentation in fscrypt_nokey_name format. diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index dbced2937ec8..f547094100be 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -43,7 +43,7 @@ struct fscrypt_context_v2 { u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; }; -/** +/* * fscrypt_context - the encryption context of an inode * * This is the on-disk equivalent of an fscrypt_policy, stored alongside each @@ -157,7 +157,7 @@ fscrypt_policy_flags(const union fscrypt_policy *policy) BUG(); } -/** +/* * For encrypted symlinks, the ciphertext length is stored at the beginning * of the string in little-endian format. */ diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 4ca167017d67..0b5077e4759a 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -9,7 +9,7 @@ #include "fscrypt_private.h" /** - * fscrypt_file_open - prepare to open a possibly-encrypted regular file + * fscrypt_file_open() - prepare to open a possibly-encrypted regular file * @inode: the inode being opened * @filp: the struct file being set up * @@ -261,7 +261,7 @@ err_free_sd: EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink); /** - * fscrypt_get_symlink - get the target of an encrypted symlink + * fscrypt_get_symlink() - get the target of an encrypted symlink * @inode: the symlink inode * @caddr: the on-disk contents of the symlink * @max_size: size of @caddr buffer diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index c0b30ea18f11..49d33aad93e8 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -475,7 +475,8 @@ out: EXPORT_SYMBOL(fscrypt_get_encryption_info); /** - * fscrypt_put_encryption_info - free most of an inode's fscrypt data + * fscrypt_put_encryption_info() - free most of an inode's fscrypt data + * @inode: an inode being evicted * * Free the inode's fscrypt_info. Filesystems must call this when the inode is * being evicted. An RCU grace period need not have elapsed yet. @@ -488,7 +489,8 @@ void fscrypt_put_encryption_info(struct inode *inode) EXPORT_SYMBOL(fscrypt_put_encryption_info); /** - * fscrypt_free_inode - free an inode's fscrypt data requiring RCU delay + * fscrypt_free_inode() - free an inode's fscrypt data requiring RCU delay + * @inode: an inode being freed * * Free the inode's cached decrypted symlink target, if any. Filesystems must * call this after an RCU grace period, just before they free the inode. @@ -503,7 +505,8 @@ void fscrypt_free_inode(struct inode *inode) EXPORT_SYMBOL(fscrypt_free_inode); /** - * fscrypt_drop_inode - check whether the inode's master key has been removed + * fscrypt_drop_inode() - check whether the inode's master key has been removed + * @inode: an inode being considered for eviction * * Filesystems supporting fscrypt must call this from their ->drop_inode() * method so that encrypted inodes are evicted as soon as they're no longer in diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 10ccf945020c..0a95537fcef9 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -16,7 +16,9 @@ #include "fscrypt_private.h" /** - * fscrypt_policies_equal - check whether two encryption policies are the same + * fscrypt_policies_equal() - check whether two encryption policies are the same + * @policy1: the first policy + * @policy2: the second policy * * Return: %true if equal, else %false */ @@ -170,7 +172,9 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, } /** - * fscrypt_supported_policy - check whether an encryption policy is supported + * fscrypt_supported_policy() - check whether an encryption policy is supported + * @policy_u: the encryption policy + * @inode: the inode on which the policy will be used * * Given an encryption policy, check whether all its encryption modes and other * settings are supported by this kernel on the given inode. (But we don't @@ -192,7 +196,10 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, } /** - * fscrypt_new_context_from_policy - create a new fscrypt_context from a policy + * fscrypt_new_context_from_policy() - create a new fscrypt_context from + * an fscrypt_policy + * @ctx_u: output context + * @policy_u: input policy * * Create an fscrypt_context for an inode that is being assigned the given * encryption policy. A new nonce is randomly generated. @@ -242,7 +249,11 @@ static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u, } /** - * fscrypt_policy_from_context - convert an fscrypt_context to an fscrypt_policy + * fscrypt_policy_from_context() - convert an fscrypt_context to + * an fscrypt_policy + * @policy_u: output policy + * @ctx_u: input context + * @ctx_size: size of input context in bytes * * Given an fscrypt_context, build the corresponding fscrypt_policy. * diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index a2314004416e..24426587dfe3 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -75,6 +75,7 @@ static inline bool fscrypt_has_encryption_key(const struct inode *inode) /** * fscrypt_needs_contents_encryption() - check whether an inode needs * contents encryption + * @inode: the inode to check * * Return: %true iff the inode is an encrypted regular file and the kernel was * built with fscrypt support. @@ -493,7 +494,7 @@ static inline const char *fscrypt_get_symlink(struct inode *inode, #endif /* !CONFIG_FS_ENCRYPTION */ /** - * fscrypt_require_key - require an inode's encryption key + * fscrypt_require_key() - require an inode's encryption key * @inode: the inode we need the key for * * If the inode is encrypted, set up its encryption key if not already done. @@ -519,7 +520,8 @@ static inline int fscrypt_require_key(struct inode *inode) } /** - * fscrypt_prepare_link - prepare to link an inode into a possibly-encrypted directory + * fscrypt_prepare_link() - prepare to link an inode into a possibly-encrypted + * directory * @old_dentry: an existing dentry for the inode being linked * @dir: the target directory * @dentry: negative dentry for the target filename @@ -546,7 +548,8 @@ static inline int fscrypt_prepare_link(struct dentry *old_dentry, } /** - * fscrypt_prepare_rename - prepare for a rename between possibly-encrypted directories + * fscrypt_prepare_rename() - prepare for a rename between possibly-encrypted + * directories * @old_dir: source directory * @old_dentry: dentry for source file * @new_dir: target directory @@ -579,7 +582,8 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir, } /** - * fscrypt_prepare_lookup - prepare to lookup a name in a possibly-encrypted directory + * fscrypt_prepare_lookup() - prepare to lookup a name in a possibly-encrypted + * directory * @dir: directory being searched * @dentry: filename being looked up * @fname: (output) the name to use to search the on-disk directory @@ -612,7 +616,8 @@ static inline int fscrypt_prepare_lookup(struct inode *dir, } /** - * fscrypt_prepare_setattr - prepare to change a possibly-encrypted inode's attributes + * fscrypt_prepare_setattr() - prepare to change a possibly-encrypted inode's + * attributes * @dentry: dentry through which the inode is being changed * @attr: attributes to change * @@ -637,7 +642,7 @@ static inline int fscrypt_prepare_setattr(struct dentry *dentry, } /** - * fscrypt_prepare_symlink - prepare to create a possibly-encrypted symlink + * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink * @dir: directory in which the symlink is being created * @target: plaintext symlink target * @len: length of @target excluding null terminator @@ -676,7 +681,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir, } /** - * fscrypt_encrypt_symlink - encrypt the symlink target if needed + * fscrypt_encrypt_symlink() - encrypt the symlink target if needed * @inode: symlink inode * @target: plaintext symlink target * @len: length of @target excluding null terminator From 0cea915cdbd8ebc2726f1e31c2f243ba47267c92 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:57 -0700 Subject: [PATCH 002/162] fscrypt: name all function parameters Name all the function parameters. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fscrypt patches. This also matches the checkpatch expectation. Link: https://lore.kernel.org/r/20200511191358.53096-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 46 ++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 24426587dfe3..b320fcf301a9 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -56,10 +56,11 @@ struct fscrypt_name { struct fscrypt_operations { unsigned int flags; const char *key_prefix; - int (*get_context)(struct inode *, void *, size_t); - int (*set_context)(struct inode *, const void *, size_t, void *); - bool (*dummy_context)(struct inode *); - bool (*empty_dir)(struct inode *); + int (*get_context)(struct inode *inode, void *ctx, size_t len); + int (*set_context)(struct inode *inode, const void *ctx, size_t len, + void *fs_data); + bool (*dummy_context)(struct inode *inode); + bool (*empty_dir)(struct inode *inode); unsigned int max_namelen; bool (*has_stable_inodes)(struct super_block *sb); void (*get_ino_and_lblk_bits)(struct super_block *sb, @@ -137,13 +138,15 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) extern void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); -extern int fscrypt_ioctl_get_policy(struct file *, void __user *); -extern int fscrypt_ioctl_get_policy_ex(struct file *, void __user *); +extern int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); +extern int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); +extern int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); extern int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); -extern int fscrypt_has_permitted_context(struct inode *, struct inode *); -extern int fscrypt_inherit_context(struct inode *, struct inode *, - void *, bool); +extern int fscrypt_has_permitted_context(struct inode *parent, + struct inode *child); +extern int fscrypt_inherit_context(struct inode *parent, struct inode *child, + void *fs_data, bool preload); + /* keyring.c */ extern void fscrypt_sb_free(struct super_block *sb); extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); @@ -153,23 +156,24 @@ extern int fscrypt_ioctl_remove_key_all_users(struct file *filp, extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ -extern int fscrypt_get_encryption_info(struct inode *); -extern void fscrypt_put_encryption_info(struct inode *); -extern void fscrypt_free_inode(struct inode *); +extern int fscrypt_get_encryption_info(struct inode *inode); +extern void fscrypt_put_encryption_info(struct inode *inode); +extern void fscrypt_free_inode(struct inode *inode); extern int fscrypt_drop_inode(struct inode *inode); /* fname.c */ -extern int fscrypt_setup_filename(struct inode *, const struct qstr *, - int lookup, struct fscrypt_name *); +extern int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, + int lookup, struct fscrypt_name *fname); static inline void fscrypt_free_filename(struct fscrypt_name *fname) { kfree(fname->crypto_buf.name); } -extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, - struct fscrypt_str *); -extern void fscrypt_fname_free_buffer(struct fscrypt_str *); +extern int fscrypt_fname_alloc_buffer(const struct inode *inode, + u32 max_encrypted_len, + struct fscrypt_str *crypto_str); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); extern int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, @@ -180,9 +184,9 @@ extern u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); /* bio.c */ -extern void fscrypt_decrypt_bio(struct bio *); -extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, - unsigned int); +extern void fscrypt_decrypt_bio(struct bio *bio); +extern int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len); /* hooks.c */ extern int fscrypt_file_open(struct inode *inode, struct file *filp); From de635b5d05e152b4d1d64b17b63f28e4e88959cb Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:58 -0700 Subject: [PATCH 003/162] fscrypt: remove unnecessary extern keywords Remove the unnecessary 'extern' keywords from function declarations. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fscrypt patches. This also makes the code shorter and matches the 'checkpatch --strict' expectation. Link: https://lore.kernel.org/r/20200511191358.53096-4-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/crypto/fscrypt_private.h | 82 ++++++++++----------- include/linux/fscrypt.h | 139 ++++++++++++++++++------------------ 2 files changed, 107 insertions(+), 114 deletions(-) diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index f547094100be..20cbd9a4b28b 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -231,15 +231,14 @@ typedef enum { /* crypto.c */ extern struct kmem_cache *fscrypt_info_cachep; -extern int fscrypt_initialize(unsigned int cop_flags); -extern int fscrypt_crypt_block(const struct inode *inode, - fscrypt_direction_t rw, u64 lblk_num, - struct page *src_page, struct page *dest_page, - unsigned int len, unsigned int offs, - gfp_t gfp_flags); -extern struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags); +int fscrypt_initialize(unsigned int cop_flags); +int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, + u64 lblk_num, struct page *src_page, + struct page *dest_page, unsigned int len, + unsigned int offs, gfp_t gfp_flags); +struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags); -extern void __printf(3, 4) __cold +void __printf(3, 4) __cold fscrypt_msg(const struct inode *inode, const char *level, const char *fmt, ...); #define fscrypt_warn(inode, fmt, ...) \ @@ -264,12 +263,10 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, const struct fscrypt_info *ci); /* fname.c */ -extern int fscrypt_fname_encrypt(const struct inode *inode, - const struct qstr *iname, - u8 *out, unsigned int olen); -extern bool fscrypt_fname_encrypted_size(const struct inode *inode, - u32 orig_len, u32 max_len, - u32 *encrypted_len_ret); +int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, + u8 *out, unsigned int olen); +bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len, + u32 max_len, u32 *encrypted_len_ret); extern const struct dentry_operations fscrypt_d_ops; /* hkdf.c */ @@ -278,8 +275,8 @@ struct fscrypt_hkdf { struct crypto_shash *hmac_tfm; }; -extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, - unsigned int master_key_size); +int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, + unsigned int master_key_size); /* * The list of contexts in which fscrypt uses HKDF. These values are used as @@ -294,11 +291,11 @@ extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, #define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 #define HKDF_CONTEXT_DIRHASH_KEY 5 -extern int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, - const u8 *info, unsigned int infolen, - u8 *okm, unsigned int okmlen); +int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, + const u8 *info, unsigned int infolen, + u8 *okm, unsigned int okmlen); -extern void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf); +void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf); /* keyring.c */ @@ -436,14 +433,14 @@ static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec) return 0; } -extern struct key * +struct key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec); -extern int fscrypt_verify_key_added(struct super_block *sb, - const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); +int fscrypt_verify_key_added(struct super_block *sb, + const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); -extern int __init fscrypt_init_keyring(void); +int __init fscrypt_init_keyring(void); /* keysetup.c */ @@ -457,33 +454,32 @@ struct fscrypt_mode { extern struct fscrypt_mode fscrypt_modes[]; -extern struct crypto_skcipher * -fscrypt_allocate_skcipher(struct fscrypt_mode *mode, const u8 *raw_key, - const struct inode *inode); +struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode, + const u8 *raw_key, + const struct inode *inode); -extern int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, - const u8 *raw_key); +int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key); -extern int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, - const struct fscrypt_master_key *mk); +int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, + const struct fscrypt_master_key *mk); /* keysetup_v1.c */ -extern void fscrypt_put_direct_key(struct fscrypt_direct_key *dk); +void fscrypt_put_direct_key(struct fscrypt_direct_key *dk); -extern int fscrypt_setup_v1_file_key(struct fscrypt_info *ci, - const u8 *raw_master_key); +int fscrypt_setup_v1_file_key(struct fscrypt_info *ci, + const u8 *raw_master_key); + +int fscrypt_setup_v1_file_key_via_subscribed_keyrings(struct fscrypt_info *ci); -extern int fscrypt_setup_v1_file_key_via_subscribed_keyrings( - struct fscrypt_info *ci); /* policy.c */ -extern bool fscrypt_policies_equal(const union fscrypt_policy *policy1, - const union fscrypt_policy *policy2); -extern bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, - const struct inode *inode); -extern int fscrypt_policy_from_context(union fscrypt_policy *policy_u, - const union fscrypt_context *ctx_u, - int ctx_size); +bool fscrypt_policies_equal(const union fscrypt_policy *policy1, + const union fscrypt_policy *policy2); +bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, + const struct inode *inode); +int fscrypt_policy_from_context(union fscrypt_policy *policy_u, + const union fscrypt_context *ctx_u, + int ctx_size); #endif /* _FSCRYPT_PRIVATE_H */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index b320fcf301a9..959be1270e3f 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -108,22 +108,21 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) } /* crypto.c */ -extern void fscrypt_enqueue_decrypt_work(struct work_struct *); +void fscrypt_enqueue_decrypt_work(struct work_struct *); -extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, - unsigned int len, - unsigned int offs, - gfp_t gfp_flags); -extern int fscrypt_encrypt_block_inplace(const struct inode *inode, - struct page *page, unsigned int len, - unsigned int offs, u64 lblk_num, - gfp_t gfp_flags); +struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, + unsigned int len, + unsigned int offs, + gfp_t gfp_flags); +int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num, gfp_t gfp_flags); -extern int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, - unsigned int offs); -extern int fscrypt_decrypt_block_inplace(const struct inode *inode, - struct page *page, unsigned int len, - unsigned int offs, u64 lblk_num); +int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, + unsigned int offs); +int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num); static inline bool fscrypt_is_bounce_page(struct page *page) { @@ -135,81 +134,79 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return (struct page *)page_private(bounce_page); } -extern void fscrypt_free_bounce_page(struct page *bounce_page); +void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); -extern int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); -extern int fscrypt_has_permitted_context(struct inode *parent, - struct inode *child); -extern int fscrypt_inherit_context(struct inode *parent, struct inode *child, - void *fs_data, bool preload); +int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); +int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); +int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); +int fscrypt_inherit_context(struct inode *parent, struct inode *child, + void *fs_data, bool preload); /* keyring.c */ -extern void fscrypt_sb_free(struct super_block *sb); -extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_remove_key_all_users(struct file *filp, - void __user *arg); -extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); +void fscrypt_sb_free(struct super_block *sb); +int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); +int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); +int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ -extern int fscrypt_get_encryption_info(struct inode *inode); -extern void fscrypt_put_encryption_info(struct inode *inode); -extern void fscrypt_free_inode(struct inode *inode); -extern int fscrypt_drop_inode(struct inode *inode); +int fscrypt_get_encryption_info(struct inode *inode); +void fscrypt_put_encryption_info(struct inode *inode); +void fscrypt_free_inode(struct inode *inode); +int fscrypt_drop_inode(struct inode *inode); /* fname.c */ -extern int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, - int lookup, struct fscrypt_name *fname); +int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, + int lookup, struct fscrypt_name *fname); static inline void fscrypt_free_filename(struct fscrypt_name *fname) { kfree(fname->crypto_buf.name); } -extern int fscrypt_fname_alloc_buffer(const struct inode *inode, - u32 max_encrypted_len, - struct fscrypt_str *crypto_str); -extern void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); -extern int fscrypt_fname_disk_to_usr(const struct inode *inode, - u32 hash, u32 minor_hash, - const struct fscrypt_str *iname, - struct fscrypt_str *oname); -extern bool fscrypt_match_name(const struct fscrypt_name *fname, - const u8 *de_name, u32 de_name_len); -extern u64 fscrypt_fname_siphash(const struct inode *dir, - const struct qstr *name); +int fscrypt_fname_alloc_buffer(const struct inode *inode, u32 max_encrypted_len, + struct fscrypt_str *crypto_str); +void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); +int fscrypt_fname_disk_to_usr(const struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname); +bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len); +u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); /* bio.c */ -extern void fscrypt_decrypt_bio(struct bio *bio); -extern int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, - sector_t pblk, unsigned int len); +void fscrypt_decrypt_bio(struct bio *bio); +int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len); /* hooks.c */ -extern int fscrypt_file_open(struct inode *inode, struct file *filp); -extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, - struct dentry *dentry); -extern int __fscrypt_prepare_rename(struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry, - unsigned int flags); -extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, - struct fscrypt_name *fname); -extern int fscrypt_prepare_setflags(struct inode *inode, - unsigned int oldflags, unsigned int flags); -extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, - unsigned int max_len, - struct fscrypt_str *disk_link); -extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, - unsigned int len, - struct fscrypt_str *disk_link); -extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, - unsigned int max_size, - struct delayed_call *done); +int fscrypt_file_open(struct inode *inode, struct file *filp); +int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, + struct dentry *dentry); +int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags); +int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *fname); +int fscrypt_prepare_setflags(struct inode *inode, + unsigned int oldflags, unsigned int flags); +int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link); +int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, + unsigned int len, struct fscrypt_str *disk_link); +const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, + unsigned int max_size, + struct delayed_call *done); +static inline void fscrypt_set_ops(struct super_block *sb, + const struct fscrypt_operations *s_cop) +{ + sb->s_cop = s_cop; +} #else /* !CONFIG_FS_ENCRYPTION */ static inline bool fscrypt_has_encryption_key(const struct inode *inode) From ddceea270a7d33d48f0ab1316ca226905ec1a2b5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:48 -0700 Subject: [PATCH 004/162] linux/parser.h: add include guards is missing include guards. Add them. This is needed to allow declaring a function in that takes a substring_t parameter. Link: https://lore.kernel.org/r/20200512233251.118314-2-ebiggers@kernel.org Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- include/linux/parser.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/linux/parser.h b/include/linux/parser.h index 12fc3482f5fc..89e2b23fb888 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -7,7 +7,8 @@ * but could potentially be used anywhere else that simple option=arg * parsing is required. */ - +#ifndef _LINUX_PARSER_H +#define _LINUX_PARSER_H /* associates an integer enumerator with a pattern string. */ struct match_token { @@ -34,3 +35,5 @@ int match_hex(substring_t *, int *result); bool match_wildcard(const char *pattern, const char *str); size_t match_strlcpy(char *, const substring_t *, size_t); char *match_strdup(const substring_t *); + +#endif /* _LINUX_PARSER_H */ From 6dc3cb5f238a6b761c1fe067f67ccf9caae70cc3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:49 -0700 Subject: [PATCH 005/162] fscrypt: add fscrypt_add_test_dummy_key() Currently, the test_dummy_encryption mount option (which is used for encryption I/O testing with xfstests) uses v1 encryption policies, and it relies on userspace inserting a test key into the session keyring. We need test_dummy_encryption to support v2 encryption policies too. Requiring userspace to add the test key doesn't work well with v2 policies, since v2 policies only support the filesystem keyring (not the session keyring), and keys in the filesystem keyring are lost when the filesystem is unmounted. Hooking all test code that unmounts and re-mounts the filesystem would be difficult. Instead, let's make the filesystem automatically add the test key to its keyring when test_dummy_encryption is enabled. That puts the responsibility for choosing the test key on the kernel. We could just hard-code a key. But out of paranoia, let's first try using a per-boot random key, to prevent this code from being misused. A per-boot key will work as long as no one expects dummy-encrypted files to remain accessible after a reboot. (gce-xfstests doesn't.) Therefore, this patch adds a function fscrypt_add_test_dummy_key() which implements the above. The next patch will use it. Link: https://lore.kernel.org/r/20200512233251.118314-3-ebiggers@kernel.org Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- fs/crypto/fscrypt_private.h | 3 + fs/crypto/keyring.c | 119 +++++++++++++++++++++++------------- 2 files changed, 78 insertions(+), 44 deletions(-) diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 20cbd9a4b28b..855ea935f5a6 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -437,6 +437,9 @@ struct key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec); +int fscrypt_add_test_dummy_key(struct super_block *sb, + struct fscrypt_key_specifier *key_spec); + int fscrypt_verify_key_added(struct super_block *sb, const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 35ffabfffbf8..f86e36060aae 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -20,6 +20,7 @@ #include #include +#include #include #include "fscrypt_private.h" @@ -424,9 +425,9 @@ static int add_existing_master_key(struct fscrypt_master_key *mk, return 0; } -static int add_master_key(struct super_block *sb, - struct fscrypt_master_key_secret *secret, - const struct fscrypt_key_specifier *mk_spec) +static int do_add_master_key(struct super_block *sb, + struct fscrypt_master_key_secret *secret, + const struct fscrypt_key_specifier *mk_spec) { static DEFINE_MUTEX(fscrypt_add_key_mutex); struct key *key; @@ -465,6 +466,35 @@ out_unlock: return err; } +static int add_master_key(struct super_block *sb, + struct fscrypt_master_key_secret *secret, + struct fscrypt_key_specifier *key_spec) +{ + int err; + + if (key_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { + err = fscrypt_init_hkdf(&secret->hkdf, secret->raw, + secret->size); + if (err) + return err; + + /* + * Now that the HKDF context is initialized, the raw key is no + * longer needed. + */ + memzero_explicit(secret->raw, secret->size); + + /* Calculate the key identifier */ + err = fscrypt_hkdf_expand(&secret->hkdf, + HKDF_CONTEXT_KEY_IDENTIFIER, NULL, 0, + key_spec->u.identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE); + if (err) + return err; + } + return do_add_master_key(sb, secret, key_spec); +} + static int fscrypt_provisioning_key_preparse(struct key_preparsed_payload *prep) { const struct fscrypt_provisioning_key_payload *payload = prep->data; @@ -609,6 +639,15 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg) if (memchr_inv(arg.__reserved, 0, sizeof(arg.__reserved))) return -EINVAL; + /* + * Only root can add keys that are identified by an arbitrary descriptor + * rather than by a cryptographic hash --- since otherwise a malicious + * user could add the wrong key. + */ + if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && + !capable(CAP_SYS_ADMIN)) + return -EACCES; + memset(&secret, 0, sizeof(secret)); if (arg.key_id) { if (arg.raw_size != 0) @@ -626,54 +665,46 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg) goto out_wipe_secret; } - switch (arg.key_spec.type) { - case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR: - /* - * Only root can add keys that are identified by an arbitrary - * descriptor rather than by a cryptographic hash --- since - * otherwise a malicious user could add the wrong key. - */ - err = -EACCES; - if (!capable(CAP_SYS_ADMIN)) - goto out_wipe_secret; - break; - case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER: - err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size); - if (err) - goto out_wipe_secret; - - /* - * Now that the HKDF context is initialized, the raw key is no - * longer needed. - */ - memzero_explicit(secret.raw, secret.size); - - /* Calculate the key identifier and return it to userspace. */ - err = fscrypt_hkdf_expand(&secret.hkdf, - HKDF_CONTEXT_KEY_IDENTIFIER, - NULL, 0, arg.key_spec.u.identifier, - FSCRYPT_KEY_IDENTIFIER_SIZE); - if (err) - goto out_wipe_secret; - err = -EFAULT; - if (copy_to_user(uarg->key_spec.u.identifier, - arg.key_spec.u.identifier, - FSCRYPT_KEY_IDENTIFIER_SIZE)) - goto out_wipe_secret; - break; - default: - WARN_ON(1); - err = -EINVAL; - goto out_wipe_secret; - } - err = add_master_key(sb, &secret, &arg.key_spec); + if (err) + goto out_wipe_secret; + + /* Return the key identifier to userspace, if applicable */ + err = -EFAULT; + if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER && + copy_to_user(uarg->key_spec.u.identifier, arg.key_spec.u.identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE)) + goto out_wipe_secret; + err = 0; out_wipe_secret: wipe_master_key_secret(&secret); return err; } EXPORT_SYMBOL_GPL(fscrypt_ioctl_add_key); +/* + * Add the key for '-o test_dummy_encryption' to the filesystem keyring. + * + * Use a per-boot random key to prevent people from misusing this option. + */ +int fscrypt_add_test_dummy_key(struct super_block *sb, + struct fscrypt_key_specifier *key_spec) +{ + static u8 test_key[FSCRYPT_MAX_KEY_SIZE]; + struct fscrypt_master_key_secret secret; + int err; + + get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE); + + memset(&secret, 0, sizeof(secret)); + secret.size = FSCRYPT_MAX_KEY_SIZE; + memcpy(secret.raw, test_key, FSCRYPT_MAX_KEY_SIZE); + + err = add_master_key(sb, &secret, key_spec); + wipe_master_key_secret(&secret); + return err; +} + /* * Verify that the current user has added a master key with the given identifier * (returns -ENOKEY if not). This is needed to prevent a user from encrypting From 11807f32791ac8f46cc8ff6a67cb99c48305524e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:50 -0700 Subject: [PATCH 006/162] fscrypt: support test_dummy_encryption=v2 v1 encryption policies are deprecated in favor of v2, and some new features (e.g. encryption+casefolding) are only being added for v2. Therefore, the "test_dummy_encryption" mount option (which is used for encryption I/O testing with xfstests) needs to support v2 policies. To do this, extend its syntax to be "test_dummy_encryption=v1" or "test_dummy_encryption=v2". The existing "test_dummy_encryption" (no argument) also continues to be accepted, to specify the default setting -- currently v1, but the next patch changes it to v2. To cleanly support both v1 and v2 while also making it easy to support specifying other encryption settings in the future (say, accepting "$contents_mode:$filenames_mode:v2"), make ext4 and f2fs maintain a pointer to the dummy fscrypt_context rather than using mount flags. To avoid concurrency issues, don't allow test_dummy_encryption to be set or changed during a remount. (The former restriction is new, but xfstests doesn't run into it, so no one should notice.) Tested with 'gce-xfstests -c {ext4,f2fs}/encrypt -g auto'. On ext4, there are two regressions, both of which are test bugs: ext4/023 and ext4/028 fail because they set an xattr and expect it to be stored inline, but the increase in size of the fscrypt_context from 24 to 40 bytes causes this xattr to be spilled into an external block. Link: https://lore.kernel.org/r/20200512233251.118314-4-ebiggers@kernel.org Acked-by: Jaegeuk Kim Reviewed-by: Theodore Ts'o Signed-off-by: Eric Biggers --- Documentation/filesystems/f2fs.txt | 6 +- fs/crypto/keysetup.c | 15 ++-- fs/crypto/policy.c | 125 +++++++++++++++++++++++++++++ fs/ext4/ext4.h | 8 +- fs/ext4/super.c | 66 ++++++++++++--- fs/ext4/sysfs.c | 2 + fs/f2fs/f2fs.h | 4 +- fs/f2fs/super.c | 85 ++++++++++++++------ fs/f2fs/sysfs.c | 4 + include/linux/fscrypt.h | 51 ++++++++++-- 10 files changed, 308 insertions(+), 58 deletions(-) diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index 1ca9556ec849..76603ab3851b 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -217,8 +217,12 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix", pass, but the performance will regress. "nobarrier" is based on "posix", but doesn't issue flush command for non-atomic files likewise "nobarrier" mount option. -test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt +test_dummy_encryption +test_dummy_encryption=%s + Enable dummy encryption, which provides a fake fscrypt context. The fake fscrypt context is used by xfstests. + The argument may be either "v1" or "v2", in order to + select the corresponding fscrypt policy version. checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enable" to reenable checkpointing. Is enabled by default. While disabled, any unmounting or unexpected shutdowns will cause diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 49d33aad93e8..04d014c0c64e 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -395,21 +395,18 @@ int fscrypt_get_encryption_info(struct inode *inode) res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); if (res < 0) { - if (!fscrypt_dummy_context_enabled(inode) || - IS_ENCRYPTED(inode)) { + const union fscrypt_context *dummy_ctx = + fscrypt_get_dummy_context(inode->i_sb); + + if (IS_ENCRYPTED(inode) || !dummy_ctx) { fscrypt_warn(inode, "Error %d getting encryption context", res); return res; } /* Fake up a context for an unencrypted directory */ - memset(&ctx, 0, sizeof(ctx)); - ctx.version = FSCRYPT_CONTEXT_V1; - ctx.v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS; - ctx.v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS; - memset(ctx.v1.master_key_descriptor, 0x42, - FSCRYPT_KEY_DESCRIPTOR_SIZE); - res = sizeof(ctx.v1); + res = fscrypt_context_size(dummy_ctx); + memcpy(&ctx, dummy_ctx, res); } crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 0a95537fcef9..bcab94b29d10 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -11,6 +11,7 @@ */ #include +#include #include #include #include "fscrypt_private.h" @@ -616,3 +617,127 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, return preload ? fscrypt_get_encryption_info(child): 0; } EXPORT_SYMBOL(fscrypt_inherit_context); + +/** + * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption' + * @sb: the filesystem on which test_dummy_encryption is being specified + * @arg: the argument to the test_dummy_encryption option. + * If no argument was specified, then @arg->from == NULL. + * @dummy_ctx: the filesystem's current dummy context (input/output, see below) + * + * Handle the test_dummy_encryption mount option by creating a dummy encryption + * context, saving it in @dummy_ctx, and adding the corresponding dummy + * encryption key to the filesystem. If the @dummy_ctx is already set, then + * instead validate that it matches @arg. Don't support changing it via + * remount, as that is difficult to do safely. + * + * The reason we use an fscrypt_context rather than an fscrypt_policy is because + * we mustn't generate a new nonce each time we access a dummy-encrypted + * directory, as that would change the way filenames are encrypted. + * + * Return: 0 on success (dummy context set, or the same context is already set); + * -EEXIST if a different dummy context is already set; + * or another -errno value. + */ +int fscrypt_set_test_dummy_encryption(struct super_block *sb, + const substring_t *arg, + struct fscrypt_dummy_context *dummy_ctx) +{ + const char *argstr = "v1"; + const char *argstr_to_free = NULL; + struct fscrypt_key_specifier key_spec = { 0 }; + int version; + union fscrypt_context *ctx = NULL; + int err; + + if (arg->from) { + argstr = argstr_to_free = match_strdup(arg); + if (!argstr) + return -ENOMEM; + } + + if (!strcmp(argstr, "v1")) { + version = FSCRYPT_CONTEXT_V1; + key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR; + memset(key_spec.u.descriptor, 0x42, + FSCRYPT_KEY_DESCRIPTOR_SIZE); + } else if (!strcmp(argstr, "v2")) { + version = FSCRYPT_CONTEXT_V2; + key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; + /* key_spec.u.identifier gets filled in when adding the key */ + } else { + err = -EINVAL; + goto out; + } + + if (dummy_ctx->ctx) { + /* + * Note: if we ever make test_dummy_encryption support + * specifying other encryption settings, such as the encryption + * modes, we'll need to compare those settings here. + */ + if (dummy_ctx->ctx->version == version) + err = 0; + else + err = -EEXIST; + goto out; + } + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + err = -ENOMEM; + goto out; + } + + err = fscrypt_add_test_dummy_key(sb, &key_spec); + if (err) + goto out; + + ctx->version = version; + switch (ctx->version) { + case FSCRYPT_CONTEXT_V1: + ctx->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS; + ctx->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS; + memcpy(ctx->v1.master_key_descriptor, key_spec.u.descriptor, + FSCRYPT_KEY_DESCRIPTOR_SIZE); + break; + case FSCRYPT_CONTEXT_V2: + ctx->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS; + ctx->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS; + memcpy(ctx->v2.master_key_identifier, key_spec.u.identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE); + break; + default: + WARN_ON(1); + err = -EINVAL; + goto out; + } + dummy_ctx->ctx = ctx; + ctx = NULL; + err = 0; +out: + kfree(ctx); + kfree(argstr_to_free); + return err; +} +EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption); + +/** + * fscrypt_show_test_dummy_encryption() - show '-o test_dummy_encryption' + * @seq: the seq_file to print the option to + * @sep: the separator character to use + * @sb: the filesystem whose options are being shown + * + * Show the test_dummy_encryption mount option, if it was specified. + * This is mainly used for /proc/mounts. + */ +void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, + struct super_block *sb) +{ + const union fscrypt_context *ctx = fscrypt_get_dummy_context(sb); + + if (!ctx) + return; + seq_printf(seq, "%ctest_dummy_encryption=v%d", sep, ctx->version); +} +EXPORT_SYMBOL_GPL(fscrypt_show_test_dummy_encryption); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f933c35fdcc1..56deb1c0fe79 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1355,11 +1355,9 @@ struct ext4_super_block { */ #define EXT4_MF_MNTDIR_SAMPLED 0x0001 #define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ -#define EXT4_MF_TEST_DUMMY_ENCRYPTION 0x0004 #ifdef CONFIG_FS_ENCRYPTION -#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \ - EXT4_MF_TEST_DUMMY_ENCRYPTION)) +#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_ctx.ctx != NULL) #else #define DUMMY_ENCRYPTION_ENABLED(sbi) (0) #endif @@ -1550,8 +1548,12 @@ struct ext4_sb_info { struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; + /* Encryption context for '-o test_dummy_encryption' */ + struct fscrypt_dummy_context s_dummy_enc_ctx; + /* Barrier between changing inodes' journal flags and writepages ops. */ struct percpu_rw_semaphore s_journal_flag_rwsem; + struct dax_device *s_daxdev; }; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 066941be4812..1b0b24c10fc8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -952,6 +952,7 @@ static void ext4_put_super(struct super_block *sb) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev); + fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx); #ifdef CONFIG_UNICODE utf8_unload(sbi->s_encoding); #endif @@ -1234,9 +1235,10 @@ retry: return res; } -static bool ext4_dummy_context(struct inode *inode) +static const union fscrypt_context * +ext4_get_dummy_context(struct super_block *sb) { - return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb)); + return EXT4_SB(sb)->s_dummy_enc_ctx.ctx; } static bool ext4_has_stable_inodes(struct super_block *sb) @@ -1255,7 +1257,7 @@ static const struct fscrypt_operations ext4_cryptops = { .key_prefix = "ext4:", .get_context = ext4_get_context, .set_context = ext4_set_context, - .dummy_context = ext4_dummy_context, + .get_dummy_context = ext4_get_dummy_context, .empty_dir = ext4_empty_dir, .max_namelen = EXT4_NAME_LEN, .has_stable_inodes = ext4_has_stable_inodes, @@ -1445,6 +1447,7 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, + {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, {Opt_nombcache, "nombcache"}, {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ @@ -1654,7 +1657,7 @@ static const struct mount_opts { {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, {Opt_max_dir_size_kb, 0, MOPT_GTE0}, - {Opt_test_dummy_encryption, 0, MOPT_GTE0}, + {Opt_test_dummy_encryption, 0, MOPT_STRING}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_err, 0, 0} }; @@ -1689,6 +1692,48 @@ static int ext4_sb_read_encoding(const struct ext4_super_block *es, } #endif +static int ext4_set_test_dummy_encryption(struct super_block *sb, + const char *opt, + const substring_t *arg, + bool is_remount) +{ +#ifdef CONFIG_FS_ENCRYPTION + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; + + /* + * This mount option is just for testing, and it's not worthwhile to + * implement the extra complexity (e.g. RCU protection) that would be + * needed to allow it to be set or changed during remount. We do allow + * it to be specified during remount, but only if there is no change. + */ + if (is_remount && !sbi->s_dummy_enc_ctx.ctx) { + ext4_msg(sb, KERN_WARNING, + "Can't set test_dummy_encryption on remount"); + return -1; + } + err = fscrypt_set_test_dummy_encryption(sb, arg, &sbi->s_dummy_enc_ctx); + if (err) { + if (err == -EEXIST) + ext4_msg(sb, KERN_WARNING, + "Can't change test_dummy_encryption on remount"); + else if (err == -EINVAL) + ext4_msg(sb, KERN_WARNING, + "Value of option \"%s\" is unrecognized", opt); + else + ext4_msg(sb, KERN_WARNING, + "Error processing option \"%s\" [%d]", + opt, err); + return -1; + } + ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); +#else + ext4_msg(sb, KERN_WARNING, + "Test dummy encryption mount option ignored"); +#endif + return 1; +} + static int handle_mount_opt(struct super_block *sb, char *opt, int token, substring_t *args, unsigned long *journal_devnum, unsigned int *journal_ioprio, int is_remount) @@ -1871,14 +1916,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg); } else if (token == Opt_test_dummy_encryption) { -#ifdef CONFIG_FS_ENCRYPTION - sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION; - ext4_msg(sb, KERN_WARNING, - "Test dummy encryption mode enabled"); -#else - ext4_msg(sb, KERN_WARNING, - "Test dummy encryption mount option ignored"); -#endif + return ext4_set_test_dummy_encryption(sb, opt, &args[0], + is_remount); } else if (m->flags & MOPT_DATAJ) { if (is_remount) { if (!sbi->s_journal) @@ -2131,6 +2170,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); + fscrypt_show_test_dummy_encryption(seq, sep, sb); + ext4_show_quota_options(seq, sb); return 0; } @@ -4510,6 +4551,7 @@ failed_mount: for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(sbi->s_qf_names[i]); #endif + fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx); ext4_blkdev_remove(sbi); brelse(bh); out_fail: diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 76a32f2b5944..df6039f5db3b 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -226,6 +226,7 @@ EXT4_ATTR_FEATURE(batched_discard); EXT4_ATTR_FEATURE(meta_bg_resize); #ifdef CONFIG_FS_ENCRYPTION EXT4_ATTR_FEATURE(encryption); +EXT4_ATTR_FEATURE(test_dummy_encryption_v2); #endif #ifdef CONFIG_UNICODE EXT4_ATTR_FEATURE(casefold); @@ -241,6 +242,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(meta_bg_resize), #ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), + ATTR_LIST(test_dummy_encryption_v2), #endif #ifdef CONFIG_UNICODE ATTR_LIST(casefold), diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8eef4a676a90..974eae36d979 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -138,7 +138,7 @@ struct f2fs_mount_info { int fsync_mode; /* fsync policy */ int fs_mode; /* fs mode: LFS or ADAPTIVE */ int bggc_mode; /* bggc mode: off, on or sync */ - bool test_dummy_encryption; /* test dummy encryption */ + struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */ block_t unusable_cap_perc; /* percentage for cap */ block_t unusable_cap; /* Amount of space allowed to be * unusable when disabling checkpoint @@ -1312,7 +1312,7 @@ enum fsync_mode { #ifdef CONFIG_FS_ENCRYPTION #define DUMMY_ENCRYPTION_ENABLED(sbi) \ - (unlikely(F2FS_OPTION(sbi).test_dummy_encryption)) + (unlikely(F2FS_OPTION(sbi).dummy_enc_ctx.ctx != NULL)) #else #define DUMMY_ENCRYPTION_ENABLED(sbi) (0) #endif diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 0775ee36cb21..1a4899141cbd 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -201,6 +201,7 @@ static match_table_t f2fs_tokens = { {Opt_whint, "whint_mode=%s"}, {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, + {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, {Opt_checkpoint_disable, "checkpoint=disable"}, {Opt_checkpoint_disable_cap, "checkpoint=disable:%u"}, @@ -409,7 +410,52 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) } #endif -static int parse_options(struct super_block *sb, char *options) +static int f2fs_set_test_dummy_encryption(struct super_block *sb, + const char *opt, + const substring_t *arg, + bool is_remount) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); +#ifdef CONFIG_FS_ENCRYPTION + int err; + + if (!f2fs_sb_has_encrypt(sbi)) { + f2fs_err(sbi, "Encrypt feature is off"); + return -EINVAL; + } + + /* + * This mount option is just for testing, and it's not worthwhile to + * implement the extra complexity (e.g. RCU protection) that would be + * needed to allow it to be set or changed during remount. We do allow + * it to be specified during remount, but only if there is no change. + */ + if (is_remount && !F2FS_OPTION(sbi).dummy_enc_ctx.ctx) { + f2fs_warn(sbi, "Can't set test_dummy_encryption on remount"); + return -EINVAL; + } + err = fscrypt_set_test_dummy_encryption( + sb, arg, &F2FS_OPTION(sbi).dummy_enc_ctx); + if (err) { + if (err == -EEXIST) + f2fs_warn(sbi, + "Can't change test_dummy_encryption on remount"); + else if (err == -EINVAL) + f2fs_warn(sbi, "Value of option \"%s\" is unrecognized", + opt); + else + f2fs_warn(sbi, "Error processing option \"%s\" [%d]", + opt, err); + return -EINVAL; + } + f2fs_warn(sbi, "Test dummy encryption mode enabled"); +#else + f2fs_warn(sbi, "Test dummy encryption mount option ignored"); +#endif + return 0; +} + +static int parse_options(struct super_block *sb, char *options, bool is_remount) { struct f2fs_sb_info *sbi = F2FS_SB(sb); substring_t args[MAX_OPT_ARGS]; @@ -418,9 +464,7 @@ static int parse_options(struct super_block *sb, char *options) int arg = 0, ext_cnt; kuid_t uid; kgid_t gid; -#ifdef CONFIG_QUOTA int ret; -#endif if (!options) return 0; @@ -783,17 +827,10 @@ static int parse_options(struct super_block *sb, char *options) kvfree(name); break; case Opt_test_dummy_encryption: -#ifdef CONFIG_FS_ENCRYPTION - if (!f2fs_sb_has_encrypt(sbi)) { - f2fs_err(sbi, "Encrypt feature is off"); - return -EINVAL; - } - - F2FS_OPTION(sbi).test_dummy_encryption = true; - f2fs_info(sbi, "Test dummy encryption mode enabled"); -#else - f2fs_info(sbi, "Test dummy encryption mount option ignored"); -#endif + ret = f2fs_set_test_dummy_encryption(sb, p, &args[0], + is_remount); + if (ret) + return ret; break; case Opt_checkpoint_disable_cap_perc: if (args->from && match_int(args, &arg)) @@ -1219,6 +1256,7 @@ static void f2fs_put_super(struct super_block *sb) for (i = 0; i < MAXQUOTAS; i++) kvfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif + fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx); destroy_percpu_info(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); @@ -1550,10 +1588,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",whint_mode=%s", "user-based"); else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) seq_printf(seq, ",whint_mode=%s", "fs-based"); -#ifdef CONFIG_FS_ENCRYPTION - if (F2FS_OPTION(sbi).test_dummy_encryption) - seq_puts(seq, ",test_dummy_encryption"); -#endif + + fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb); if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT) seq_printf(seq, ",alloc_mode=%s", "default"); @@ -1582,7 +1618,6 @@ static void default_options(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; - F2FS_OPTION(sbi).test_dummy_encryption = false; F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID); F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4; @@ -1741,7 +1776,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) default_options(sbi); /* parse mount options */ - err = parse_options(sb, data); + err = parse_options(sb, data, true); if (err) goto restore_opts; checkpoint_changed = @@ -2418,9 +2453,10 @@ static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len, ctx, len, fs_data, XATTR_CREATE); } -static bool f2fs_dummy_context(struct inode *inode) +static const union fscrypt_context * +f2fs_get_dummy_context(struct super_block *sb) { - return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode)); + return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_ctx.ctx; } static bool f2fs_has_stable_inodes(struct super_block *sb) @@ -2439,7 +2475,7 @@ static const struct fscrypt_operations f2fs_cryptops = { .key_prefix = "f2fs:", .get_context = f2fs_get_context, .set_context = f2fs_set_context, - .dummy_context = f2fs_dummy_context, + .get_dummy_context = f2fs_get_dummy_context, .empty_dir = f2fs_empty_dir, .max_namelen = F2FS_NAME_LEN, .has_stable_inodes = f2fs_has_stable_inodes, @@ -3395,7 +3431,7 @@ try_onemore: goto free_sb_buf; } - err = parse_options(sb, options); + err = parse_options(sb, options, false); if (err) goto free_options; @@ -3787,6 +3823,7 @@ free_options: for (i = 0; i < MAXQUOTAS; i++) kvfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif + fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx); kvfree(options); free_sb_buf: kvfree(raw_super); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 321ab382946a..8f53ef414a2b 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -455,6 +455,7 @@ enum feat_id { FEAT_SB_CHECKSUM, FEAT_CASEFOLD, FEAT_COMPRESSION, + FEAT_TEST_DUMMY_ENCRYPTION_V2, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -475,6 +476,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_SB_CHECKSUM: case FEAT_CASEFOLD: case FEAT_COMPRESSION: + case FEAT_TEST_DUMMY_ENCRYPTION_V2: return sprintf(buf, "supported\n"); } return 0; @@ -575,6 +577,7 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks); #ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); +F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2, FEAT_TEST_DUMMY_ENCRYPTION_V2); #endif #ifdef CONFIG_BLK_DEV_ZONED F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED); @@ -661,6 +664,7 @@ static struct attribute *f2fs_attrs[] = { static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), + ATTR_LIST(test_dummy_encryption_v2), #endif #ifdef CONFIG_BLK_DEV_ZONED ATTR_LIST(block_zoned), diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 959be1270e3f..d81beb99ee7b 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -15,12 +15,15 @@ #include #include +#include #include #include #define FS_CRYPTO_BLOCK_SIZE 16 +union fscrypt_context; struct fscrypt_info; +struct seq_file; struct fscrypt_str { unsigned char *name; @@ -59,7 +62,8 @@ struct fscrypt_operations { int (*get_context)(struct inode *inode, void *ctx, size_t len); int (*set_context)(struct inode *inode, const void *ctx, size_t len, void *fs_data); - bool (*dummy_context)(struct inode *inode); + const union fscrypt_context *(*get_dummy_context)( + struct super_block *sb); bool (*empty_dir)(struct inode *inode); unsigned int max_namelen; bool (*has_stable_inodes)(struct super_block *sb); @@ -89,10 +93,12 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); } -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +static inline const union fscrypt_context * +fscrypt_get_dummy_context(struct super_block *sb) { - return inode->i_sb->s_cop->dummy_context && - inode->i_sb->s_cop->dummy_context(inode); + if (!sb->s_cop->get_dummy_context) + return NULL; + return sb->s_cop->get_dummy_context(sb); } /* @@ -145,6 +151,22 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); int fscrypt_inherit_context(struct inode *parent, struct inode *child, void *fs_data, bool preload); +struct fscrypt_dummy_context { + const union fscrypt_context *ctx; +}; + +int fscrypt_set_test_dummy_encryption(struct super_block *sb, + const substring_t *arg, + struct fscrypt_dummy_context *dummy_ctx); +void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, + struct super_block *sb); +static inline void +fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +{ + kfree(dummy_ctx->ctx); + dummy_ctx->ctx = NULL; +} + /* keyring.c */ void fscrypt_sb_free(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); @@ -219,9 +241,10 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) return false; } -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +static inline const union fscrypt_context * +fscrypt_get_dummy_context(struct super_block *sb) { - return false; + return NULL; } static inline void fscrypt_handle_d_move(struct dentry *dentry) @@ -316,6 +339,20 @@ static inline int fscrypt_inherit_context(struct inode *parent, return -EOPNOTSUPP; } +struct fscrypt_dummy_context { +}; + +static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, + char sep, + struct super_block *sb) +{ +} + +static inline void +fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +{ +} + /* keyring.c */ static inline void fscrypt_sb_free(struct super_block *sb) { @@ -671,7 +708,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir, unsigned int max_len, struct fscrypt_str *disk_link) { - if (IS_ENCRYPTED(dir) || fscrypt_dummy_context_enabled(dir)) + if (IS_ENCRYPTED(dir) || fscrypt_get_dummy_context(dir->i_sb) != NULL) return __fscrypt_prepare_symlink(dir, len, max_len, disk_link); disk_link->name = (unsigned char *)target; From 7c2fcbe7ae97435d1be7b10667c6f6f9d17f4683 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:51 -0700 Subject: [PATCH 007/162] fscrypt: make test_dummy_encryption use v2 by default Since v1 encryption policies are deprecated, make test_dummy_encryption test v2 policies by default. Note that this causes ext4/023 and ext4/028 to start failing due to known bugs in those tests (see previous commit). Link: https://lore.kernel.org/r/20200512233251.118314-5-ebiggers@kernel.org Reviewed-by: Jaegeuk Kim Reviewed-by: Theodore Ts'o Signed-off-by: Eric Biggers --- fs/crypto/policy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index bcab94b29d10..a15aec8e068c 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -643,7 +643,7 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb, const substring_t *arg, struct fscrypt_dummy_context *dummy_ctx) { - const char *argstr = "v1"; + const char *argstr = "v2"; const char *argstr_to_free = NULL; struct fscrypt_key_specifier key_spec = { 0 }; int version; From 84aad2655054ef9882ae60d5876f0d6fd103ee2a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 May 2020 13:41:41 -0700 Subject: [PATCH 008/162] fscrypt: add support for IV_INO_LBLK_32 policies The eMMC inline crypto standard will only specify 32 DUN bits (a.k.a. IV bits), unlike UFS's 64. IV_INO_LBLK_64 is therefore not applicable, but an encryption format which uses one key per policy and permits the moving of encrypted file contents (as f2fs's garbage collector requires) is still desirable. To support such hardware, add a new encryption format IV_INO_LBLK_32 that makes the best use of the 32 bits: the IV is set to 'SipHash-2-4(inode_number) + file_logical_block_number mod 2^32', where the SipHash key is derived from the fscrypt master key. We hash only the inode number and not also the block number, because we need to maintain contiguity of DUNs to merge bios. Unlike with IV_INO_LBLK_64, with this format IV reuse is possible; this is unavoidable given the size of the DUN. This means this format should only be used where the requirements of the first paragraph apply. However, the hash spreads out the IVs in the whole usable range, and the use of a keyed hash makes it difficult for an attacker to determine which files use which IVs. Besides the above differences, this flag works like IV_INO_LBLK_64 in that on ext4 it is only allowed if the stable_inodes feature has been enabled to prevent inode numbers and the filesystem UUID from changing. Link: https://lore.kernel.org/r/20200515204141.251098-1-ebiggers@kernel.org Reviewed-by: Theodore Ts'o Reviewed-by: Paul Crowley Signed-off-by: Eric Biggers --- Documentation/filesystems/fscrypt.rst | 33 +++++++++-- fs/crypto/crypto.c | 6 +- fs/crypto/fscrypt_private.h | 20 +++++-- fs/crypto/keyring.c | 5 +- fs/crypto/keysetup.c | 85 +++++++++++++++++++++------ fs/crypto/policy.c | 51 +++++++++++----- include/uapi/linux/fscrypt.h | 3 +- 7 files changed, 157 insertions(+), 46 deletions(-) diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index dc444b8d3704..7f9a372031fd 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -292,8 +292,22 @@ files' data differently, inode numbers are included in the IVs. Consequently, shrinking the filesystem may not be allowed. This format is optimized for use with inline encryption hardware -compliant with the UFS or eMMC standards, which support only 64 IV -bits per I/O request and may have only a small number of keyslots. +compliant with the UFS standard, which supports only 64 IV bits per +I/O request and may have only a small number of keyslots. + +IV_INO_LBLK_32 policies +----------------------- + +IV_INO_LBLK_32 policies work like IV_INO_LBLK_64, except that for +IV_INO_LBLK_32, the inode number is hashed with SipHash-2-4 (where the +SipHash key is derived from the master key) and added to the file +logical block number mod 2^32 to produce a 32-bit IV. + +This format is optimized for use with inline encryption hardware +compliant with the eMMC v5.2 standard, which supports only 32 IV bits +per I/O request and may have only a small number of keyslots. This +format results in some level of IV reuse, so it should only be used +when necessary due to hardware limitations. Key identifiers --------------- @@ -369,6 +383,10 @@ a little endian number, except that: to 32 bits and is placed in bits 0-31 of the IV. The inode number (which is also limited to 32 bits) is placed in bits 32-63. +- With `IV_INO_LBLK_32 policies`_, the logical block number is limited + to 32 bits and is placed in bits 0-31 of the IV. The inode number + is then hashed and added mod 2^32. + Note that because file logical block numbers are included in the IVs, filesystems must enforce that blocks are never shifted around within encrypted files, e.g. via "collapse range" or "insert range". @@ -465,8 +483,15 @@ This structure must be initialized as follows: (0x3). - FSCRYPT_POLICY_FLAG_DIRECT_KEY: See `DIRECT_KEY policies`_. - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64: See `IV_INO_LBLK_64 - policies`_. This is mutually exclusive with DIRECT_KEY and is not - supported on v1 policies. + policies`_. + - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32: See `IV_INO_LBLK_32 + policies`_. + + v1 encryption policies only support the PAD_* and DIRECT_KEY flags. + The other flags are only supported by v2 encryption policies. + + The DIRECT_KEY, IV_INO_LBLK_64, and IV_INO_LBLK_32 flags are + mutually exclusive. - For v2 encryption policies, ``__reserved`` must be zeroed. diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index e56da1d6b2e7..6845f742b69c 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -76,8 +76,12 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, memset(iv, 0, ci->ci_mode->ivsize); if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { - WARN_ON_ONCE((u32)lblk_num != lblk_num); + WARN_ON_ONCE(lblk_num > U32_MAX); + WARN_ON_ONCE(ci->ci_inode->i_ino > U32_MAX); lblk_num |= (u64)ci->ci_inode->i_ino << 32; + } else if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { + WARN_ON_ONCE(lblk_num > U32_MAX); + lblk_num = (u32)(ci->ci_hashed_ino + lblk_num); } else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); } diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 855ea935f5a6..eb7fcd2b7fb8 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -222,6 +222,9 @@ struct fscrypt_info { /* This inode's nonce, copied from the fscrypt_context */ u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + + /* Hashed inode number. Only set for IV_INO_LBLK_32 */ + u32 ci_hashed_ino; }; typedef enum { @@ -290,6 +293,8 @@ int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, #define HKDF_CONTEXT_DIRECT_KEY 3 #define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 #define HKDF_CONTEXT_DIRHASH_KEY 5 +#define HKDF_CONTEXT_IV_INO_LBLK_32_KEY 6 +#define HKDF_CONTEXT_INODE_HASH_KEY 7 int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, const u8 *info, unsigned int infolen, @@ -386,14 +391,17 @@ struct fscrypt_master_key { struct list_head mk_decrypted_inodes; spinlock_t mk_decrypted_inodes_lock; - /* Crypto API transforms for DIRECT_KEY policies, allocated on-demand */ - struct crypto_skcipher *mk_direct_tfms[__FSCRYPT_MODE_MAX + 1]; - /* - * Crypto API transforms for filesystem-layer implementation of - * IV_INO_LBLK_64 policies, allocated on-demand. + * Per-mode encryption keys for the various types of encryption policies + * that use them. Allocated and derived on-demand. */ - struct crypto_skcipher *mk_iv_ino_lblk_64_tfms[__FSCRYPT_MODE_MAX + 1]; + struct crypto_skcipher *mk_direct_keys[__FSCRYPT_MODE_MAX + 1]; + struct crypto_skcipher *mk_iv_ino_lblk_64_keys[__FSCRYPT_MODE_MAX + 1]; + struct crypto_skcipher *mk_iv_ino_lblk_32_keys[__FSCRYPT_MODE_MAX + 1]; + + /* Hash key for inode numbers. Initialized only when needed. */ + siphash_key_t mk_ino_hash_key; + bool mk_ino_hash_key_initialized; } __randomize_layout; diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index f86e36060aae..47724a95555c 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -45,8 +45,9 @@ static void free_master_key(struct fscrypt_master_key *mk) wipe_master_key_secret(&mk->mk_secret); for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) { - crypto_free_skcipher(mk->mk_direct_tfms[i]); - crypto_free_skcipher(mk->mk_iv_ino_lblk_64_tfms[i]); + crypto_free_skcipher(mk->mk_direct_keys[i]); + crypto_free_skcipher(mk->mk_iv_ino_lblk_64_keys[i]); + crypto_free_skcipher(mk->mk_iv_ino_lblk_32_keys[i]); } key_put(mk->mk_users); diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 04d014c0c64e..9a5f7e7dbea4 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -46,6 +46,8 @@ struct fscrypt_mode fscrypt_modes[] = { }, }; +static DEFINE_MUTEX(fscrypt_mode_key_setup_mutex); + static struct fscrypt_mode * select_encryption_mode(const union fscrypt_policy *policy, const struct inode *inode) @@ -130,7 +132,7 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, const struct super_block *sb = inode->i_sb; struct fscrypt_mode *mode = ci->ci_mode; const u8 mode_num = mode - fscrypt_modes; - struct crypto_skcipher *tfm, *prev_tfm; + struct crypto_skcipher *tfm; u8 mode_key[FSCRYPT_MAX_KEY_SIZE]; u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; unsigned int hkdf_infolen = 0; @@ -139,10 +141,17 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX)) return -EINVAL; - /* pairs with cmpxchg() below */ + /* pairs with smp_store_release() below */ tfm = READ_ONCE(tfms[mode_num]); - if (likely(tfm != NULL)) - goto done; + if (likely(tfm != NULL)) { + ci->ci_ctfm = tfm; + return 0; + } + + mutex_lock(&fscrypt_mode_key_setup_mutex); + + if (tfms[mode_num]) + goto done_unlock; BUILD_BUG_ON(sizeof(mode_num) != 1); BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); @@ -157,21 +166,21 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, hkdf_context, hkdf_info, hkdf_infolen, mode_key, mode->keysize); if (err) - return err; + goto out_unlock; tfm = fscrypt_allocate_skcipher(mode, mode_key, inode); memzero_explicit(mode_key, mode->keysize); - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - /* pairs with READ_ONCE() above */ - prev_tfm = cmpxchg(&tfms[mode_num], NULL, tfm); - if (prev_tfm != NULL) { - crypto_free_skcipher(tfm); - tfm = prev_tfm; + if (IS_ERR(tfm)) { + err = PTR_ERR(tfm); + goto out_unlock; } -done: + /* pairs with READ_ONCE() above */ + smp_store_release(&tfms[mode_num], tfm); +done_unlock: ci->ci_ctfm = tfm; - return 0; + err = 0; +out_unlock: + mutex_unlock(&fscrypt_mode_key_setup_mutex); + return err; } int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, @@ -189,6 +198,43 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, return 0; } +static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_info *ci, + struct fscrypt_master_key *mk) +{ + int err; + + err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_32_keys, + HKDF_CONTEXT_IV_INO_LBLK_32_KEY, true); + if (err) + return err; + + /* pairs with smp_store_release() below */ + if (!smp_load_acquire(&mk->mk_ino_hash_key_initialized)) { + + mutex_lock(&fscrypt_mode_key_setup_mutex); + + if (mk->mk_ino_hash_key_initialized) + goto unlock; + + err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, + HKDF_CONTEXT_INODE_HASH_KEY, NULL, 0, + (u8 *)&mk->mk_ino_hash_key, + sizeof(mk->mk_ino_hash_key)); + if (err) + goto unlock; + /* pairs with smp_load_acquire() above */ + smp_store_release(&mk->mk_ino_hash_key_initialized, true); +unlock: + mutex_unlock(&fscrypt_mode_key_setup_mutex); + if (err) + return err; + } + + ci->ci_hashed_ino = (u32)siphash_1u64(ci->ci_inode->i_ino, + &mk->mk_ino_hash_key); + return 0; +} + static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, struct fscrypt_master_key *mk) { @@ -203,7 +249,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, * encryption key. This ensures that the master key is * consistently used only for HKDF, avoiding key reuse issues. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_tfms, + err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_keys, HKDF_CONTEXT_DIRECT_KEY, false); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { @@ -211,11 +257,14 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, * IV_INO_LBLK_64: encryption keys are derived from (master_key, * mode_num, filesystem_uuid), and inode number is included in * the IVs. This format is optimized for use with inline - * encryption hardware compliant with the UFS or eMMC standards. + * encryption hardware compliant with the UFS standard. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_tfms, + err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_keys, HKDF_CONTEXT_IV_INO_LBLK_64_KEY, true); + } else if (ci->ci_policy.v2.flags & + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { + err = fscrypt_setup_iv_ino_lblk_32_key(ci, mk); } else { u8 derived_key[FSCRYPT_MAX_KEY_SIZE]; diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index a15aec8e068c..d23ff162c78b 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -69,18 +69,14 @@ static bool supported_direct_key_modes(const struct inode *inode, return true; } -static bool supported_iv_ino_lblk_64_policy( - const struct fscrypt_policy_v2 *policy, - const struct inode *inode) +static bool supported_iv_ino_lblk_policy(const struct fscrypt_policy_v2 *policy, + const struct inode *inode, + const char *type, + int max_ino_bits, int max_lblk_bits) { struct super_block *sb = inode->i_sb; int ino_bits = 64, lblk_bits = 64; - if (policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { - fscrypt_warn(inode, - "The DIRECT_KEY and IV_INO_LBLK_64 flags are mutually exclusive"); - return false; - } /* * It's unsafe to include inode numbers in the IVs if the filesystem can * potentially renumber inodes, e.g. via filesystem shrinking. @@ -88,16 +84,22 @@ static bool supported_iv_ino_lblk_64_policy( if (!sb->s_cop->has_stable_inodes || !sb->s_cop->has_stable_inodes(sb)) { fscrypt_warn(inode, - "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't have stable inode numbers", - sb->s_id); + "Can't use %s policy on filesystem '%s' because it doesn't have stable inode numbers", + type, sb->s_id); return false; } if (sb->s_cop->get_ino_and_lblk_bits) sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits); - if (ino_bits > 32 || lblk_bits > 32) { + if (ino_bits > max_ino_bits) { fscrypt_warn(inode, - "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't use 32-bit inode and block numbers", - sb->s_id); + "Can't use %s policy on filesystem '%s' because its inode numbers are too long", + type, sb->s_id); + return false; + } + if (lblk_bits > max_lblk_bits) { + fscrypt_warn(inode, + "Can't use %s policy on filesystem '%s' because its block numbers are too long", + type, sb->s_id); return false; } return true; @@ -140,6 +142,8 @@ static bool fscrypt_supported_v1_policy(const struct fscrypt_policy_v1 *policy, static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, const struct inode *inode) { + int count = 0; + if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode, policy->filenames_encryption_mode)) { fscrypt_warn(inode, @@ -155,13 +159,29 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, return false; } + count += !!(policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY); + count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64); + count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32); + if (count > 1) { + fscrypt_warn(inode, "Mutually exclusive encryption flags (0x%02x)", + policy->flags); + return false; + } + if ((policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) && !supported_direct_key_modes(inode, policy->contents_encryption_mode, policy->filenames_encryption_mode)) return false; if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) && - !supported_iv_ino_lblk_64_policy(policy, inode)) + !supported_iv_ino_lblk_policy(policy, inode, "IV_INO_LBLK_64", + 32, 32)) + return false; + + if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) && + /* This uses hashed inode numbers, so ino_bits doesn't matter. */ + !supported_iv_ino_lblk_policy(policy, inode, "IV_INO_LBLK_32", + INT_MAX, 32)) return false; if (memchr_inv(policy->__reserved, 0, sizeof(policy->__reserved))) { @@ -366,6 +386,9 @@ static int set_encryption_policy(struct inode *inode, policy->v2.master_key_identifier); if (err) return err; + if (policy->v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) + pr_warn_once("%s (pid %d) is setting an IV_INO_LBLK_32 encryption policy. This should only be used if there are certain hardware limitations.\n", + current->comm, current->pid); break; default: WARN_ON(1); diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index a10e3cdc2839..7875709ccfeb 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -19,7 +19,8 @@ #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 -#define FSCRYPT_POLICY_FLAGS_VALID 0x0F +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10 +#define FSCRYPT_POLICY_FLAGS_VALID 0x1F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 From 906021bc7f8526967eff8f4296bdd03628e245bf Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:21:17 -0700 Subject: [PATCH 009/162] fs-verity: fix all kerneldoc warnings Fix all kerneldoc warnings in fs/verity/ and include/linux/fsverity.h. Most of these were due to missing documentation for function parameters. Detected with: scripts/kernel-doc -v -none fs/verity/*.{c,h} include/linux/fsverity.h This cleanup makes it possible to check new patches for kerneldoc warnings without having to filter out all the existing ones. Link: https://lore.kernel.org/r/20200511192118.71427-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/verity/enable.c | 2 ++ fs/verity/fsverity_private.h | 2 +- fs/verity/measure.c | 2 ++ fs/verity/open.c | 1 + fs/verity/signature.c | 3 +++ fs/verity/verify.c | 3 +++ include/linux/fsverity.h | 3 +++ 7 files changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/verity/enable.c b/fs/verity/enable.c index 15e7d14ec2ff..d734cebaae70 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -329,6 +329,8 @@ rollback: /** * fsverity_ioctl_enable() - enable verity on a file + * @filp: file to enable verity on + * @uarg: user pointer to fsverity_enable_arg * * Enable fs-verity on a file. See the "FS_IOC_ENABLE_VERITY" section of * Documentation/filesystems/fsverity.rst for the documentation. diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index 4b2c8aed0563..c668dfc53f87 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -61,7 +61,7 @@ struct merkle_tree_params { u64 level_start[FS_VERITY_MAX_LEVELS]; }; -/** +/* * fsverity_info - cached verity metadata for an inode * * When a verity file is first opened, an instance of this struct is allocated diff --git a/fs/verity/measure.c b/fs/verity/measure.c index 05049b68c745..df409a5682ed 100644 --- a/fs/verity/measure.c +++ b/fs/verity/measure.c @@ -11,6 +11,8 @@ /** * fsverity_ioctl_measure() - get a verity file's measurement + * @filp: file to get measurement of + * @_uarg: user pointer to fsverity_digest * * Retrieve the file measurement that the kernel is enforcing for reads from a * verity file. See the "FS_IOC_MEASURE_VERITY" section of diff --git a/fs/verity/open.c b/fs/verity/open.c index 25b29065d897..71c5dc279b20 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -330,6 +330,7 @@ EXPORT_SYMBOL_GPL(fsverity_prepare_setattr); /** * fsverity_cleanup_inode() - free the inode's verity info, if present + * @inode: an inode being evicted * * Filesystems must call this on inode eviction to free ->i_verity_info. */ diff --git a/fs/verity/signature.c b/fs/verity/signature.c index 3dfc56f2cdf1..9cfd2f5ff57d 100644 --- a/fs/verity/signature.c +++ b/fs/verity/signature.c @@ -28,6 +28,9 @@ static struct key *fsverity_keyring; /** * fsverity_verify_signature() - check a verity file's signature + * @vi: the file's fsverity_info + * @desc: the file's fsverity_descriptor + * @desc_size: size of @desc * * If the file's fs-verity descriptor includes a signature of the file * measurement, verify it against the certificates in the fs-verity keyring. diff --git a/fs/verity/verify.c b/fs/verity/verify.c index 5324270cd7d4..fb4c745087ec 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -179,6 +179,7 @@ out: /** * fsverity_verify_page() - verify a data page + * @page: the page to verity * * Verify a page that has just been read from a verity file. The page must be a * pagecache page that is still locked and not yet uptodate. @@ -206,6 +207,7 @@ EXPORT_SYMBOL_GPL(fsverity_verify_page); #ifdef CONFIG_BLOCK /** * fsverity_verify_bio() - verify a 'read' bio that has just completed + * @bio: the bio to verify * * Verify a set of pages that have just been read from a verity file. The pages * must be pagecache pages that are still locked and not yet uptodate. Pages @@ -264,6 +266,7 @@ EXPORT_SYMBOL_GPL(fsverity_verify_bio); /** * fsverity_enqueue_verify_work() - enqueue work on the fs-verity workqueue + * @work: the work to enqueue * * Enqueue verification work for asynchronous processing. */ diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index ecc604e61d61..5ac30198e032 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -200,6 +200,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) /** * fsverity_active() - do reads from the inode need to go through fs-verity? + * @inode: inode to check * * This checks whether ->i_verity_info has been set. * @@ -207,6 +208,8 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) + * + * Return: true if reads need to go through fs-verity, otherwise false */ static inline bool fsverity_active(const struct inode *inode) { From bc990c874500cb2fc2cbc377f9854562ff309b5d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:21:18 -0700 Subject: [PATCH 010/162] fs-verity: remove unnecessary extern keywords Remove the unnecessary 'extern' keywords from function declarations. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fs-verity patches. This also makes the code shorter and matches the 'checkpatch --strict' expectation. Link: https://lore.kernel.org/r/20200511192118.71427-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/verity/fsverity_private.h | 2 +- include/linux/fsverity.h | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index c668dfc53f87..1ce38fded6fd 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -134,7 +134,7 @@ void __init fsverity_check_hash_algs(void); /* init.c */ -extern void __printf(3, 4) __cold +void __printf(3, 4) __cold fsverity_msg(const struct inode *inode, const char *level, const char *fmt, ...); diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 5ac30198e032..78201a6d35f6 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -121,23 +121,23 @@ static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) /* enable.c */ -extern int fsverity_ioctl_enable(struct file *filp, const void __user *arg); +int fsverity_ioctl_enable(struct file *filp, const void __user *arg); /* measure.c */ -extern int fsverity_ioctl_measure(struct file *filp, void __user *arg); +int fsverity_ioctl_measure(struct file *filp, void __user *arg); /* open.c */ -extern int fsverity_file_open(struct inode *inode, struct file *filp); -extern int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); -extern void fsverity_cleanup_inode(struct inode *inode); +int fsverity_file_open(struct inode *inode, struct file *filp); +int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); +void fsverity_cleanup_inode(struct inode *inode); /* verify.c */ -extern bool fsverity_verify_page(struct page *page); -extern void fsverity_verify_bio(struct bio *bio); -extern void fsverity_enqueue_verify_work(struct work_struct *work); +bool fsverity_verify_page(struct page *page); +void fsverity_verify_bio(struct bio *bio); +void fsverity_enqueue_verify_work(struct work_struct *work); #else /* !CONFIG_FS_VERITY */ From 3cec603f33ae9a792657c332de3fbf336522cc59 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 16 Jun 2020 15:13:37 -0700 Subject: [PATCH 011/162] fscrypt: remove stale definition Fixes wrong merge resolution only in f2fs-stable. Signed-off-by: Jaegeuk Kim --- include/linux/fscrypt.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index d81beb99ee7b..48c2869fea26 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -224,11 +224,6 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done); -static inline void fscrypt_set_ops(struct super_block *sb, - const struct fscrypt_operations *s_cop) -{ - sb->s_cop = s_cop; -} #else /* !CONFIG_FS_ENCRYPTION */ static inline bool fscrypt_has_encryption_key(const struct inode *inode) From f312c63f1c30318b53ff2606ec24f83188893323 Mon Sep 17 00:00:00 2001 From: Alistair Delva Date: Wed, 17 Jun 2020 19:04:57 -0700 Subject: [PATCH 012/162] ANDROID: Enable LZ4_RAMDISK Bug: 150391496 Change-Id: Ib742a7e98cd19d2ff5eccac78b564e3792f20eb9 Signed-off-by: Alistair Delva --- build.config.cuttlefish.aarch64 | 1 + build.config.cuttlefish.x86_64 | 1 + 2 files changed, 2 insertions(+) diff --git a/build.config.cuttlefish.aarch64 b/build.config.cuttlefish.aarch64 index 0cb601958972..02b48a171329 100644 --- a/build.config.cuttlefish.aarch64 +++ b/build.config.cuttlefish.aarch64 @@ -1,5 +1,6 @@ . ${ROOT_DIR}/common/build.config.common . ${ROOT_DIR}/common/build.config.aarch64 +LZ4_RAMDISK=1 DEFCONFIG=cuttlefish_defconfig POST_DEFCONFIG_CMDS="check_defconfig" diff --git a/build.config.cuttlefish.x86_64 b/build.config.cuttlefish.x86_64 index fed773ccc64a..3248353e35e0 100644 --- a/build.config.cuttlefish.x86_64 +++ b/build.config.cuttlefish.x86_64 @@ -1,5 +1,6 @@ . ${ROOT_DIR}/common/build.config.common . ${ROOT_DIR}/common/build.config.x86_64 +LZ4_RAMDISK=1 DEFCONFIG=x86_64_cuttlefish_defconfig POST_DEFCONFIG_CMDS="check_defconfig" From 137526cb94e7d06d99c7b18f3093f6ba427b9707 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 19 Jun 2020 11:56:43 -0700 Subject: [PATCH 013/162] Revert "writeback: Avoid skipping inode writeback" This reverts commit 25078e97c11cebbd8598b4cbce906fa7f6bba903. --- fs/fs-writeback.c | 39 ++++++++++----------------------------- include/linux/fs.h | 7 +------ 2 files changed, 11 insertions(+), 35 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 79dff82ee2e9..245c430a2e41 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -160,9 +160,7 @@ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); - assert_spin_locked(&inode->i_lock); - inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } @@ -992,9 +990,7 @@ void inode_io_list_del(struct inode *inode) struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); - spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); - spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } @@ -1043,9 +1039,8 @@ void sb_clear_inode_writeback(struct inode *inode) * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ -static void __redirty_tail(struct inode *inode, struct bdi_writeback *wb) +static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { - assert_spin_locked(&inode->i_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -1054,14 +1049,6 @@ static void __redirty_tail(struct inode *inode, struct bdi_writeback *wb) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); - inode->i_state &= ~I_SYNC_QUEUED; -} - -static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) -{ - spin_lock(&inode->i_lock); - __redirty_tail(inode, wb); - spin_unlock(&inode->i_lock); } /* @@ -1130,11 +1117,8 @@ static int move_expired_inodes(struct list_head *delaying_queue, break; list_move(&inode->i_io_list, &tmp); moved++; - spin_lock(&inode->i_lock); if (flags & EXPIRE_DIRTY_ATIME) - inode->i_state |= I_DIRTY_TIME_EXPIRED; - inode->i_state |= I_SYNC_QUEUED; - spin_unlock(&inode->i_lock); + set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) @@ -1277,7 +1261,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * writeback is not making progress due to locked * buffers. Skip this inode for now. */ - __redirty_tail(inode, wb); + redirty_tail(inode, wb); return; } @@ -1297,7 +1281,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ - __redirty_tail(inode, wb); + redirty_tail(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* @@ -1305,11 +1289,10 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * such as delayed allocation during submission or metadata * updates after data IO completion. */ - __redirty_tail(inode, wb); + redirty_tail(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); - inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); @@ -1553,9 +1536,8 @@ static long writeback_sb_inodes(struct super_block *sb, */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { - inode->i_state &= ~I_SYNC_QUEUED; - __redirty_tail(inode, wb); spin_unlock(&inode->i_lock); + redirty_tail(inode, wb); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { @@ -2145,12 +2127,11 @@ void __mark_inode_dirty(struct inode *inode, int flags) inode->i_state |= flags; /* - * If the inode is queued for writeback by flush worker, just - * update its dirty state. Once the flush worker is done with - * the inode it will place it on the appropriate superblock - * list, based upon its state. + * If the inode is being synced, just update its dirty state. + * The unlocker will place the inode on the appropriate + * superblock list, based upon its state. */ - if (inode->i_state & I_SYNC_QUEUED) + if (inode->i_state & I_SYNC) goto out_unlock_inode; /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 6b7a19fd2443..d07269956030 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1997,10 +1997,6 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * - * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. - * Used to detect that mark_inode_dirty() should not move - * inode between dirty lists. - * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2021,8 +2017,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) -#define I_SYNC_QUEUED (1 << 16) +#define I_OVL_INUSE (1 << 14) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) From e11ead2b8658a2d83908bc509744b79729aeaad1 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 10 Jun 2020 17:36:03 +0200 Subject: [PATCH 014/162] writeback: Protect inode->i_io_list with inode->i_lock Currently, operations on inode->i_io_list are protected by wb->list_lock. In the following patches we'll need to maintain consistency between inode->i_state and inode->i_io_list so change the code so that inode->i_lock protects also all inode's i_io_list handling. Reviewed-by: Martijn Coenen Reviewed-by: Christoph Hellwig CC: stable@vger.kernel.org # Prerequisite for "writeback: Avoid skipping inode writeback" Signed-off-by: Jan Kara --- fs/fs-writeback.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 245c430a2e41..5f4d1e593973 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -160,6 +160,7 @@ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); @@ -990,7 +991,9 @@ void inode_io_list_del(struct inode *inode) struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); + spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); + spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } @@ -1039,8 +1042,10 @@ void sb_clear_inode_writeback(struct inode *inode) * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ -static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { + assert_spin_locked(&inode->i_lock); + if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -1051,6 +1056,13 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) inode_io_list_move_locked(inode, wb, &wb->b_dirty); } +static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +{ + spin_lock(&inode->i_lock); + redirty_tail_locked(inode, wb); + spin_unlock(&inode->i_lock); +} + /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ @@ -1261,7 +1273,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * writeback is not making progress due to locked * buffers. Skip this inode for now. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); return; } @@ -1281,7 +1293,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* @@ -1289,7 +1301,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * such as delayed allocation during submission or metadata * updates after data IO completion. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); @@ -1536,8 +1548,8 @@ static long writeback_sb_inodes(struct super_block *sb, */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); - redirty_tail(inode, wb); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { From 37343fde13a6ed576a0846856c4d88de7a5f5a06 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 29 May 2020 15:05:22 +0200 Subject: [PATCH 015/162] writeback: Avoid skipping inode writeback Inode's i_io_list list head is used to attach inode to several different lists - wb->{b_dirty, b_dirty_time, b_io, b_more_io}. When flush worker prepares a list of inodes to writeback e.g. for sync(2), it moves inodes to b_io list. Thus it is critical for sync(2) data integrity guarantees that inode is not requeued to any other writeback list when inode is queued for processing by flush worker. That's the reason why writeback_single_inode() does not touch i_io_list (unless the inode is completely clean) and why __mark_inode_dirty() does not touch i_io_list if I_SYNC flag is set. However there are two flaws in the current logic: 1) When inode has only I_DIRTY_TIME set but it is already queued in b_io list due to sync(2), concurrent __mark_inode_dirty(inode, I_DIRTY_SYNC) can still move inode back to b_dirty list resulting in skipping writeback of inode time stamps during sync(2). 2) When inode is on b_dirty_time list and writeback_single_inode() races with __mark_inode_dirty() like: writeback_single_inode() __mark_inode_dirty(inode, I_DIRTY_PAGES) inode->i_state |= I_SYNC __writeback_single_inode() inode->i_state |= I_DIRTY_PAGES; if (inode->i_state & I_SYNC) bail if (!(inode->i_state & I_DIRTY_ALL)) - not true so nothing done We end up with I_DIRTY_PAGES inode on b_dirty_time list and thus standard background writeback will not writeback this inode leading to possible dirty throttling stalls etc. (thanks to Martijn Coenen for this analysis). Fix these problems by tracking whether inode is queued in b_io or b_more_io lists in a new I_SYNC_QUEUED flag. When this flag is set, we know flush worker has queued inode and we should not touch i_io_list. On the other hand we also know that once flush worker is done with the inode it will requeue the inode to appropriate dirty list. When I_SYNC_QUEUED is not set, __mark_inode_dirty() can (and must) move inode to appropriate dirty list. Reported-by: Martijn Coenen Reviewed-by: Martijn Coenen Tested-by: Martijn Coenen Reviewed-by: Christoph Hellwig Fixes: 0ae45f63d4ef ("vfs: add support for a lazytime mount option") CC: stable@vger.kernel.org Signed-off-by: Jan Kara --- fs/fs-writeback.c | 17 ++++++++++++----- include/linux/fs.h | 10 +++++++--- 2 files changed, 19 insertions(+), 8 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 5f4d1e593973..14d899af1f24 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -162,6 +162,7 @@ static void inode_io_list_del_locked(struct inode *inode, assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); + inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } @@ -1054,6 +1055,7 @@ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); + inode->i_state &= ~I_SYNC_QUEUED; } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) @@ -1129,8 +1131,11 @@ static int move_expired_inodes(struct list_head *delaying_queue, break; list_move(&inode->i_io_list, &tmp); moved++; + spin_lock(&inode->i_lock); if (flags & EXPIRE_DIRTY_ATIME) - set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state); + inode->i_state |= I_DIRTY_TIME_EXPIRED; + inode->i_state |= I_SYNC_QUEUED; + spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) @@ -1305,6 +1310,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); @@ -2139,11 +2145,12 @@ void __mark_inode_dirty(struct inode *inode, int flags) inode->i_state |= flags; /* - * If the inode is being synced, just update its dirty state. - * The unlocker will place the inode on the appropriate - * superblock list, based upon its state. + * If the inode is queued for writeback by flush worker, just + * update its dirty state. Once the flush worker is done with + * the inode it will place it on the appropriate superblock + * list, based upon its state. */ - if (inode->i_state & I_SYNC) + if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* diff --git a/include/linux/fs.h b/include/linux/fs.h index d07269956030..200753b77492 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1997,6 +1997,10 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2014,10 +2018,10 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define __I_DIRTY_TIME_EXPIRED 12 -#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) +#define I_DIRTY_TIME_EXPIRED (1 << 12) #define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) +#define I_OVL_INUSE (1 << 14) +#define I_SYNC_QUEUED (1 << 17) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) From 418c9b9130438c0611873641d95aa203d59d4b60 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 29 May 2020 16:08:58 +0200 Subject: [PATCH 016/162] writeback: Fix sync livelock due to b_dirty_time processing When we are processing writeback for sync(2), move_expired_inodes() didn't set any inode expiry value (older_than_this). This can result in writeback never completing if there's steady stream of inodes added to b_dirty_time list as writeback rechecks dirty lists after each writeback round whether there's more work to be done. Fix the problem by using sync(2) start time is inode expiry value when processing b_dirty_time list similarly as for ordinarily dirtied inodes. This requires some refactoring of older_than_this handling which simplifies the code noticeably as a bonus. Fixes: 0ae45f63d4ef ("vfs: add support for a lazytime mount option") CC: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/fs-writeback.c | 44 ++++++++++++-------------------- include/trace/events/writeback.h | 13 +++++----- 2 files changed, 23 insertions(+), 34 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 14d899af1f24..0616866e3c5b 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -45,7 +45,6 @@ struct wb_completion { struct wb_writeback_work { long nr_pages; struct super_block *sb; - unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; @@ -1101,16 +1100,13 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) #define EXPIRE_DIRTY_ATIME 0x0001 /* - * Move expired (dirtied before work->older_than_this) dirty inodes from + * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - int flags, - struct wb_writeback_work *work) + int flags, unsigned long dirtied_before) { - unsigned long *older_than_this = NULL; - unsigned long expire_time; LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; @@ -1118,16 +1114,9 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; - if ((flags & EXPIRE_DIRTY_ATIME) == 0) - older_than_this = work->older_than_this; - else if (!work->for_sync) { - expire_time = jiffies - (dirtytime_expire_interval * HZ); - older_than_this = &expire_time; - } while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (older_than_this && - inode_dirtied_after(inode, *older_than_this)) + if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; @@ -1173,18 +1162,22 @@ out: * | * +--> dequeue for IO */ -static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) +static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before) { int moved; + unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, dirtied_before); + if (!work->for_sync) + time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, - EXPIRE_DIRTY_ATIME, work); + EXPIRE_DIRTY_ATIME, time_expire_jif); if (moved) wb_io_lists_populated(wb); - trace_writeback_queue_io(wb, work, moved); + trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) @@ -1696,7 +1689,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) - queue_io(wb, &work); + queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); @@ -1716,7 +1709,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * - * older_than_this takes precedence over nr_to_write. So we'll only write back + * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, @@ -1724,14 +1717,11 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; - unsigned long oldest_jif; + unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; - oldest_jif = jiffies; - work->older_than_this = &oldest_jif; - blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { @@ -1765,14 +1755,14 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - oldest_jif = jiffies - + dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - oldest_jif = jiffies; + dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) - queue_io(wb, work); + queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 2e1fa7910306..3a76ca2eecd0 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -361,8 +361,9 @@ DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before, int moved), - TP_ARGS(wb, work, moved), + TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) @@ -372,19 +373,17 @@ TRACE_EVENT(writeback_queue_io, __field(unsigned int, cgroup_ino) ), TP_fast_assign( - unsigned long *older_than_this = work->older_than_this; strncpy(__entry->name, dev_name(wb->bdi->dev), 32); - __entry->older = older_than_this ? *older_than_this : 0; - __entry->age = older_than_this ? - (jiffies - *older_than_this) * 1000 / HZ : -1; + __entry->older = dirtied_before; + __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u", __entry->name, - __entry->older, /* older_than_this in jiffies */ - __entry->age, /* older_than_this in relative milliseconds */ + __entry->older, /* dirtied_before in jiffies */ + __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), __entry->cgroup_ino From 59e9f7918960bfe91e8cf117e9935e672db3d393 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 29 May 2020 16:24:43 +0200 Subject: [PATCH 017/162] writeback: Drop I_DIRTY_TIME_EXPIRE The only use of I_DIRTY_TIME_EXPIRE is to detect in __writeback_single_inode() that inode got there because flush worker decided it's time to writeback the dirty inode time stamps (either because we are syncing or because of age). However we can detect this directly in __writeback_single_inode() and there's no need for the strange propagation with I_DIRTY_TIME_EXPIRE flag. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/ext4/inode.c | 2 +- fs/fs-writeback.c | 28 +++++++++++----------------- include/linux/fs.h | 1 - include/trace/events/writeback.h | 1 - 4 files changed, 12 insertions(+), 20 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4b68bfe9e5cb..19c699e57a52 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4977,7 +4977,7 @@ static int other_inode_match(struct inode * inode, unsigned long ino, (inode->i_state & I_DIRTY_TIME)) { struct ext4_inode_info *ei = EXT4_I(inode); - inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 0616866e3c5b..b44e7444e7ec 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1105,7 +1105,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - int flags, unsigned long dirtied_before) + unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; @@ -1121,8 +1121,6 @@ static int move_expired_inodes(struct list_head *delaying_queue, list_move(&inode->i_io_list, &tmp); moved++; spin_lock(&inode->i_lock); - if (flags & EXPIRE_DIRTY_ATIME) - inode->i_state |= I_DIRTY_TIME_EXPIRED; inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) @@ -1170,11 +1168,11 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, dirtied_before); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, - EXPIRE_DIRTY_ATIME, time_expire_jif); + time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); @@ -1350,18 +1348,14 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; - if (inode->i_state & I_DIRTY_TIME) { - if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) || - wbc->sync_mode == WB_SYNC_ALL || - unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) || - unlikely(time_after(jiffies, - (inode->dirtied_time_when + - dirtytime_expire_interval * HZ)))) { - dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; - trace_writeback_lazytime(inode); - } - } else - inode->i_state &= ~I_DIRTY_TIME_EXPIRED; + if ((inode->i_state & I_DIRTY_TIME) && + ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) || + wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || + time_after(jiffies, inode->dirtied_time_when + + dirtytime_expire_interval * HZ))) { + dirty |= I_DIRTY_TIME; + trace_writeback_lazytime(inode); + } inode->i_state &= ~dirty; /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 200753b77492..e4fa7c45d632 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2018,7 +2018,6 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define I_DIRTY_TIME_EXPIRED (1 << 12) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_SYNC_QUEUED (1 << 17) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 3a76ca2eecd0..627f5759b67d 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -20,7 +20,6 @@ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ - {I_DIRTY_TIME_EXPIRED, "I_DIRTY_TIME_EXPIRED"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) From 25007e47082f4fac061b3c7fdff92f0c52a4e229 Mon Sep 17 00:00:00 2001 From: Sahitya Tummala Date: Wed, 17 Jun 2020 01:55:58 -0700 Subject: [PATCH 018/162] FROMLIST: f2fs: fix use-after-free when accessing bio->bi_crypt_context There could be a potential race between these two paths below, leading to use-after-free when accessing bio->bi_crypt_context. f2fs_write_cache_pages ->f2fs_do_write_data_page on page#1 ->f2fs_inplace_write_data ->f2fs_merge_page_bio ->add_bio_entry ->f2fs_do_write_data_page on page#2 ->f2fs_inplace_write_data ->f2fs_merge_page_bio ->f2fs_crypt_mergeable_bio ->fscrypt_mergeable_bio f2fs_write_begin on page#1 ->f2fs_wait_on_page_writeback ->f2fs_submit_merged_ipu_write ->__submit_bio The bio gets completed, calling bio_endio ->bio_uninit ->bio_crypt_free_ctx ->use-after-free issue Fix this by moving f2fs_crypt_mergeable_bio() check within add_ipu_page() so that it's done under bio_list_lock to prevent the above race. Bug: 137270441 Link: https://lore.kernel.org/linux-f2fs-devel/1592193588-21701-1-git-send-email-stummala@codeaurora.org/ Fixes: fb710731b64b ("f2fs: add inline encryption support") Signed-off-by: Sahitya Tummala Signed-off-by: Satya Tangirala Change-Id: I1bd2cfa430423ba2a8d7c1da505322ded097cd9e --- fs/f2fs/data.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 6d5d7eb867f7..10b9679bd38c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -835,9 +835,10 @@ static void del_bio_entry(struct bio_entry *be) kmem_cache_free(bio_entry_slab, be); } -static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio, +static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio, struct page *page) { + struct f2fs_sb_info *sbi = fio->sbi; enum temp_type temp; bool found = false; int ret = -EAGAIN; @@ -854,13 +855,18 @@ static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio, found = true; - if (bio_add_page(*bio, page, PAGE_SIZE, 0) == - PAGE_SIZE) { + if (page_is_mergeable(sbi, *bio, *fio->last_block, + fio->new_blkaddr) && + f2fs_crypt_mergeable_bio(*bio, + fio->page->mapping->host, + fio->page->index, fio) && + bio_add_page(*bio, page, PAGE_SIZE, 0) == + PAGE_SIZE) { ret = 0; break; } - /* bio is full */ + /* page can't be merged into bio; submit the bio */ del_bio_entry(be); __submit_bio(sbi, *bio, DATA); break; @@ -945,11 +951,6 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) trace_f2fs_submit_page_bio(page, fio); f2fs_trace_ios(fio, 0); - if (bio && (!page_is_mergeable(fio->sbi, bio, *fio->last_block, - fio->new_blkaddr) || - !f2fs_crypt_mergeable_bio(bio, fio->page->mapping->host, - fio->page->index, fio))) - f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL); alloc_new: if (!bio) { bio = __bio_alloc(fio, BIO_MAX_PAGES); @@ -961,7 +962,7 @@ alloc_new: add_bio_entry(fio->sbi, bio, page, fio->temp); } else { - if (add_ipu_page(fio->sbi, &bio, page)) + if (add_ipu_page(fio, &bio, page)) goto alloc_new; } From 3f09a767e5508d28c7282e6075b65cf86edf0c28 Mon Sep 17 00:00:00 2001 From: Alistair Delva Date: Wed, 17 Jun 2020 21:55:14 -0700 Subject: [PATCH 019/162] ANDROID: GKI: scripts: Makefile: update the lz4 command Use 'lz4' instead of 'lz4c' and increase the compression level. This also optimizes for decompression speed at this higher level. Bug: 159285792 Test: launch_cvd -kernel_path bzImage Signed-off-by: Alistair Delva Change-Id: I9604cc7d1f3600dec27ceb460f7c29d977a919b1 --- scripts/Makefile.lib | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 36fa07a8f979..85a82e22b14f 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -364,7 +364,8 @@ cmd_lzo = (cat $(filter-out FORCE,$^) | \ quiet_cmd_lz4 = LZ4 $@ cmd_lz4 = (cat $(filter-out FORCE,$^) | \ - lz4c -l -c1 stdin stdout && $(call size_append, $(filter-out FORCE,$^))) > $@ || \ + lz4 -c -l -12 --favor-decSpeed stdin stdout && \ + $(call size_append, $(filter-out FORCE,$^))) > $@ || \ (rm -f $@ ; false) # U-Boot mkimage From b92b2ec13efb95661c1d4252a40d65d0367c6b89 Mon Sep 17 00:00:00 2001 From: Alistair Delva Date: Wed, 17 Jun 2020 21:56:07 -0700 Subject: [PATCH 020/162] ANDROID: cuttlefish_defconfig: x86: Enable KERNEL_LZ4 Compress the kernel with lz4 instead of gzip. On x86 this must be controlled explicitly by kbuild, as decompressor code is prepended to the compressed kernel artifact. On arm64 this option is not needed as "make Image.lz4" can be used instead, or the Image can be compressed in a separate step. Bug: 150391496 Change-Id: I2d0ce7f937f2a952b4310f53c8b03dc8d721b050 Signed-off-by: Alistair Delva --- arch/x86/configs/x86_64_cuttlefish_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig index de115c2a6d4c..d4294036b8df 100644 --- a/arch/x86/configs/x86_64_cuttlefish_defconfig +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -1,3 +1,4 @@ +CONFIG_KERNEL_LZ4=y CONFIG_POSIX_MQUEUE=y # CONFIG_FHANDLE is not set # CONFIG_USELIB is not set From b10c4acd41e8b15cff1119e2100adf36b013b840 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 7 Oct 2019 18:12:23 -0700 Subject: [PATCH 021/162] ANDROID: ext4: Handle casefolding with encryption This adds support for encryption with casefolding. Since the name on disk is case preserving, and also encrypted, we can no longer just recompute the hash on the fly. Additionally, to avoid leaking extra information from the hash of the unencrypted name, we use siphash via an fscrypt v2 policy. The hash is stored at the end of the directory entry for all entries inside of an encrypted and casefolded directory apart from those that deal with '.' and '..'. This way, the change is backwards compatible with existing ext4 filesystems. Signed-off-by: Daniel Rosenberg Test: Boots, /data/media is case insensitive Bug: 138322712 Change-Id: I07354e3129aa07d309fbe36c002fee1af718f348 --- fs/ext4/dir.c | 51 +++++--- fs/ext4/ext4.h | 62 ++++++++-- fs/ext4/hash.c | 24 +++- fs/ext4/ialloc.c | 5 +- fs/ext4/inline.c | 41 ++++--- fs/ext4/namei.c | 310 ++++++++++++++++++++++++++++++++--------------- fs/ext4/super.c | 6 - 7 files changed, 348 insertions(+), 151 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index ee766e3bed8b..1755a1dab5d5 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -29,6 +29,8 @@ #include "ext4.h" #include "xattr.h" +#define DOTDOT_OFFSET 12 + static int ext4_dx_readdir(struct file *, struct dir_context *); /** @@ -51,6 +53,19 @@ static int is_dx_dir(struct inode *inode) return 0; } +static bool is_fake_entry(struct inode *dir, ext4_lblk_t lblk, + unsigned int offset, unsigned int blocksize) +{ + /* Entries in the first block before this value refer to . or .. */ + if (lblk == 0 && offset <= DOTDOT_OFFSET) + return true; + /* Check if this is likely the csum entry */ + if (ext4_has_metadata_csum(dir->i_sb) && offset % blocksize == + blocksize - sizeof(struct ext4_dir_entry_tail)) + return true; + return false; +} + /* * Return 0 if the directory entry is OK, and 1 if there is a problem * @@ -63,25 +78,30 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, struct inode *dir, struct file *filp, struct ext4_dir_entry_2 *de, struct buffer_head *bh, char *buf, int size, + ext4_lblk_t lblk, unsigned int offset) { const char *error_msg = NULL; const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); + const int next_offset = ((char *) de - buf) + rlen; + unsigned int blocksize = dir->i_sb->s_blocksize; + bool fake = is_fake_entry(dir, lblk, offset, blocksize); + bool next_fake = is_fake_entry(dir, lblk, next_offset, blocksize); - if (unlikely(rlen < EXT4_DIR_REC_LEN(1))) + if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; - else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) + else if (unlikely(rlen < ext4_dir_rec_len(de->name_len, + fake ? NULL : dir))) error_msg = "rec_len is too small for name_len"; else if (unlikely(((char *) de - buf) + rlen > size)) error_msg = "directory entry overrun"; - else if (unlikely(((char *) de - buf) + rlen > - size - EXT4_DIR_REC_LEN(1) && - ((char *) de - buf) + rlen != size)) { + else if (unlikely(next_offset > size - ext4_dir_rec_len(1, + next_fake ? NULL : dir) && + next_offset != size)) error_msg = "directory entry too close to block end"; - } else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; @@ -91,15 +111,15 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " - "inode=%u, rec_len=%d, name_len=%d, size=%d", + "inode=%u, rec_len=%d, lblk=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), - rlen, de->name_len, size); + rlen, lblk, size, fake); else ext4_error_inode(dir, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " - "inode=%u, rec_len=%d, name_len=%d, size=%d", + "inode=%u, rec_len=%d, lblk=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), - rlen, de->name_len, size); + rlen, lblk, size, fake); return 1; } @@ -224,7 +244,8 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, - sb->s_blocksize) < EXT4_DIR_REC_LEN(1)) + sb->s_blocksize) < ext4_dir_rec_len(1, + inode)) break; i += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); @@ -240,7 +261,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) de = (struct ext4_dir_entry_2 *) (bh->b_data + offset); if (ext4_check_dir_entry(inode, file, de, bh, bh->b_data, bh->b_size, - offset)) { + map.m_lblk, offset)) { /* * On error, skip to the next block */ @@ -265,7 +286,9 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) /* Directory is encrypted */ err = fscrypt_fname_disk_to_usr(inode, - 0, 0, &de_name, &fstr); + EXT4_DIRENT_HASH(de), + EXT4_DIRENT_MINOR_HASH(de), + &de_name, &fstr); de_name = fstr; fstr.len = save_len; if (err) @@ -640,7 +663,7 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, top = buf + buf_size; while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, - buf, buf_size, offset)) + buf, buf_size, 0, offset)) return -EFSCORRUPTED; rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); de = (struct ext4_dir_entry_2 *)((char *)de + rlen); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4aa7f6ff2596..81a42aa9c764 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1967,6 +1967,17 @@ struct ext4_dir_entry { char name[EXT4_NAME_LEN]; /* File name */ }; + +/* + * Encrypted Casefolded entries require saving the hash on disk. This structure + * followed ext4_dir_entry_2's name[name_len] at the next 4 byte aligned + * boundary. + */ +struct ext4_dir_entry_hash { + __le32 hash; + __le32 minor_hash; +}; + /* * The new version of the directory entry. Since EXT4 structures are * stored in intel byte order, and the name_len field could never be @@ -1981,6 +1992,22 @@ struct ext4_dir_entry_2 { char name[EXT4_NAME_LEN]; /* File name */ }; +/* + * Access the hashes at the end of ext4_dir_entry_2 + */ +#define EXT4_DIRENT_HASHES(entry) \ + ((struct ext4_dir_entry_hash *) \ + (((void *)(entry)) + \ + ((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND))) +#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash) +#define EXT4_DIRENT_MINOR_HASH(entry) \ + le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash) + +static inline bool ext4_hash_in_dirent(const struct inode *inode) +{ + return IS_CASEFOLDED(inode) && IS_ENCRYPTED(inode); +} + /* * This is a bogus directory entry at the end of each leaf block that * records checksums. @@ -2022,10 +2049,24 @@ struct ext4_dir_entry_tail { */ #define EXT4_DIR_PAD 4 #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) -#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ - ~EXT4_DIR_ROUND) #define EXT4_MAX_REC_LEN ((1<<16)-1) +/* + * The rec_len is dependent on the type of directory. Directories that are + * casefolded and encrypted need to store the hash as well, so we add room for + * ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should + * pass NULL for dir, as those entries do not use the extra fields. + */ +static inline unsigned int ext4_dir_rec_len(__u8 name_len, + const struct inode *dir) +{ + int rec_len = (name_len + 8 + EXT4_DIR_ROUND); + + if (dir && ext4_hash_in_dirent(dir)) + rec_len += sizeof(struct ext4_dir_entry_hash); + return (rec_len & ~EXT4_DIR_ROUND); +} + /* * If we ever get support for fs block sizes > page_size, we'll need * to remove the #if statements in the next two functions... @@ -2082,6 +2123,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) #define DX_HASH_LEGACY_UNSIGNED 3 #define DX_HASH_HALF_MD4_UNSIGNED 4 #define DX_HASH_TEA_UNSIGNED 5 +#define DX_HASH_SIPHASH 6 static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, const void *address, unsigned int length) @@ -2139,6 +2181,7 @@ struct ext4_filename { }; #define fname_name(p) ((p)->disk_name.name) +#define fname_usr_name(p) ((p)->usr_fname->name) #define fname_len(p) ((p)->disk_name.len) /* @@ -2473,21 +2516,22 @@ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, struct file *, struct ext4_dir_entry_2 *, struct buffer_head *, char *, int, - unsigned int); -#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \ + ext4_lblk_t, unsigned int); +#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, lblk, offset) \ unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \ - (de), (bh), (buf), (size), (offset))) + (de), (bh), (buf), (size), (lblk), (offset))) extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, struct fscrypt_str *ent_name); extern void ext4_htree_free_dir_info(struct dir_private_info *p); extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, + ext4_lblk_t lblk, struct buffer_head *bh, void *buf, int buf_size, struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de); -void ext4_insert_dentry(struct inode *inode, +void ext4_insert_dentry(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, struct ext4_filename *fname); @@ -2672,11 +2716,12 @@ extern int ext4_search_dir(struct buffer_head *bh, int buf_size, struct inode *dir, struct ext4_filename *fname, - unsigned int offset, + ext4_lblk_t lblk, unsigned int offset, struct ext4_dir_entry_2 **res_dir); extern int ext4_generic_delete_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, + ext4_lblk_t lblk, struct buffer_head *bh, void *entry_buf, int buf_size, @@ -3202,9 +3247,6 @@ extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t, extern int ext4_handle_dirty_dirent_node(handle_t *handle, struct inode *inode, struct buffer_head *bh); -extern int ext4_ci_compare(const struct inode *parent, - const struct qstr *fname, - const struct qstr *entry, bool quick); #define S_SHIFT 12 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index f3bc69b8d4e5..ea735403fbb1 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -201,7 +201,7 @@ static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num) * represented, and whether or not the returned hash is 32 bits or 64 * bits. 32 bit hashes will return 0 for the minor hash. */ -static int __ext4fs_dirhash(const char *name, int len, +static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { __u32 hash; @@ -261,6 +261,22 @@ static int __ext4fs_dirhash(const char *name, int len, hash = buf[0]; minor_hash = buf[1]; break; + case DX_HASH_SIPHASH: + { + struct qstr qname = QSTR_INIT(name, len); + __u64 combined_hash; + + if (fscrypt_has_encryption_key(dir)) { + combined_hash = fscrypt_fname_siphash(dir, &qname); + } else { + ext4_warning_inode(dir, "Siphash requires key"); + return -1; + } + + hash = (__u32)(combined_hash >> 32); + minor_hash = (__u32)combined_hash; + break; + } default: hinfo->hash = 0; return -1; @@ -282,7 +298,7 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len, unsigned char *buff; struct qstr qstr = {.name = name, .len = len }; - if (len && IS_CASEFOLDED(dir) && um) { + if (len && needs_casefold(dir) && um) { buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL); if (!buff) return -ENOMEM; @@ -293,12 +309,12 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len, goto opaque_seq; } - r = __ext4fs_dirhash(buff, dlen, hinfo); + r = __ext4fs_dirhash(dir, buff, dlen, hinfo); kfree(buff); return r; } opaque_seq: #endif - return __ext4fs_dirhash(name, len, hinfo); + return __ext4fs_dirhash(dir, name, len, hinfo); } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b9d4cb194462..2f76551aad09 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -464,7 +464,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, int ret = -1; if (qstr) { - hinfo.hash_version = DX_HASH_HALF_MD4; + if (ext4_hash_in_dirent(parent)) + hinfo.hash_version = DX_HASH_SIPHASH; + else + hinfo.hash_version = DX_HASH_HALF_MD4; hinfo.seed = sbi->s_hash_seed; ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo); grp = hinfo.hash; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index f737d5b1ca3b..a71cda05b630 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1016,7 +1016,7 @@ void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, offset, de_len, de->name_len, de->name, de->name_len, le32_to_cpu(de->inode)); if (ext4_check_dir_entry(dir, NULL, de, bh, - inline_start, inline_size, offset)) + inline_start, inline_size, 0, offset)) BUG(); offset += de_len; @@ -1042,7 +1042,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, int err; struct ext4_dir_entry_2 *de; - err = ext4_find_dest_de(dir, inode, iloc->bh, inline_start, + err = ext4_find_dest_de(dir, inode, 0, iloc->bh, inline_start, inline_size, fname, &de); if (err) return err; @@ -1051,7 +1051,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, err = ext4_journal_get_write_access(handle, iloc->bh); if (err) return err; - ext4_insert_dentry(inode, de, inline_size, fname); + ext4_insert_dentry(dir, inode, de, inline_size, fname); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); @@ -1120,7 +1120,7 @@ static int ext4_update_inline_dir(handle_t *handle, struct inode *dir, int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; int new_size = get_max_inline_xattr_value_size(dir, iloc); - if (new_size - old_size <= EXT4_DIR_REC_LEN(1)) + if (new_size - old_size <= ext4_dir_rec_len(1, NULL)) return -ENOSPC; ret = ext4_update_inline_data(handle, dir, @@ -1401,8 +1401,8 @@ int htree_inlinedir_to_tree(struct file *dir_file, fake.name_len = 1; strcpy(fake.name, "."); fake.rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(fake.name_len), - inline_size); + ext4_dir_rec_len(fake.name_len, NULL), + inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_OFFSET; @@ -1411,8 +1411,8 @@ int htree_inlinedir_to_tree(struct file *dir_file, fake.name_len = 2; strcpy(fake.name, ".."); fake.rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(fake.name_len), - inline_size); + ext4_dir_rec_len(fake.name_len, NULL), + inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_SIZE; @@ -1421,13 +1421,18 @@ int htree_inlinedir_to_tree(struct file *dir_file, pos += ext4_rec_len_from_disk(de->rec_len, inline_size); if (ext4_check_dir_entry(inode, dir_file, de, iloc.bh, dir_buf, - inline_size, pos)) { + inline_size, block, pos)) { ret = count; goto out; } } - ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + if (ext4_hash_in_dirent(dir)) { + hinfo->hash = EXT4_DIRENT_HASH(de); + hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); + } else { + ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) @@ -1509,8 +1514,8 @@ int ext4_read_inline_dir(struct file *file, * So we will use extra_offset and extra_size to indicate them * during the inline dir iteration. */ - dotdot_offset = EXT4_DIR_REC_LEN(1); - dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2); + dotdot_offset = ext4_dir_rec_len(1, NULL); + dotdot_size = dotdot_offset + ext4_dir_rec_len(2, NULL); extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; extra_size = extra_offset + inline_size; @@ -1545,7 +1550,7 @@ int ext4_read_inline_dir(struct file *file, * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, extra_size) - < EXT4_DIR_REC_LEN(1)) + < ext4_dir_rec_len(1, NULL)) break; i += ext4_rec_len_from_disk(de->rec_len, extra_size); @@ -1573,7 +1578,7 @@ int ext4_read_inline_dir(struct file *file, de = (struct ext4_dir_entry_2 *) (dir_buf + ctx->pos - extra_offset); if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf, - extra_size, ctx->pos)) + extra_size, 0, ctx->pos)) goto out; if (le32_to_cpu(de->inode)) { if (!dir_emit(ctx, de->name, de->name_len, @@ -1665,7 +1670,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir, EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; ret = ext4_search_dir(iloc.bh, inline_start, inline_size, - dir, fname, 0, res_dir); + dir, fname, 0, 0, res_dir); if (ret == 1) goto out_find; if (ret < 0) @@ -1678,7 +1683,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir, inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; ret = ext4_search_dir(iloc.bh, inline_start, inline_size, - dir, fname, 0, res_dir); + dir, fname, 0, 0, res_dir); if (ret == 1) goto out_find; @@ -1727,7 +1732,7 @@ int ext4_delete_inline_entry(handle_t *handle, if (err) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, bh, + err = ext4_generic_delete_entry(handle, dir, de_del, 0, bh, inline_start, inline_size, 0); if (err) goto out; @@ -1811,7 +1816,7 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) &inline_pos, &inline_size); if (ext4_check_dir_entry(dir, NULL, de, iloc.bh, inline_pos, - inline_size, offset)) { + inline_size, 0, offset)) { ext4_warning(dir->i_sb, "bad inline directory (dir #%lu) - " "inode %u, rec_len %u, name_len %d" diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b134add5a5ad..a5cc430173f9 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -276,9 +276,11 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, unsigned blocksize, struct dx_hash_info *hinfo, struct dx_map_entry map[]); static void dx_sort_map(struct dx_map_entry *map, unsigned count); -static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to, - struct dx_map_entry *offsets, int count, unsigned blocksize); -static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize); +static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from, + char *to, struct dx_map_entry *offsets, + int count, unsigned int blocksize); +static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base, + unsigned int blocksize); static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block); static int ext4_htree_next_block(struct inode *dir, __u32 hash, @@ -287,7 +289,7 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash, __u32 *start_hash); static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, - struct ext4_dir_entry_2 **res_dir); + struct ext4_dir_entry_2 **res_dir, ext4_lblk_t *lblk); static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); @@ -569,8 +571,9 @@ static inline void dx_set_limit(struct dx_entry *entries, unsigned value) static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) { - unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - - EXT4_DIR_REC_LEN(2) - infosize; + unsigned int entry_space = dir->i_sb->s_blocksize - + ext4_dir_rec_len(1, NULL) - + ext4_dir_rec_len(2, NULL) - infosize; if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -579,7 +582,8 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) static inline unsigned dx_node_limit(struct inode *dir) { - unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); + unsigned int entry_space = dir->i_sb->s_blocksize - + ext4_dir_rec_len(0, dir); if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -675,7 +679,10 @@ static struct stats dx_show_leaf(struct inode *dir, name = fname_crypto_str.name; len = fname_crypto_str.len; } - ext4fs_dirhash(dir, de->name, + if (IS_CASEFOLDED(dir)) + h.hash = EXT4_DIRENT_HASH(de); + else + ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:(E)%x.%u ", len, name, h.hash, (unsigned) ((char *) de @@ -691,7 +698,7 @@ static struct stats dx_show_leaf(struct inode *dir, (unsigned) ((char *) de - base)); #endif } - space += EXT4_DIR_REC_LEN(de->name_len); + space += ext4_dir_rec_len(de->name_len, dir); names++; } de = ext4_next_entry(de, size); @@ -763,11 +770,25 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, root = (struct dx_root *) frame->bh->b_data; if (root->info.hash_version != DX_HASH_TEA && root->info.hash_version != DX_HASH_HALF_MD4 && - root->info.hash_version != DX_HASH_LEGACY) { + root->info.hash_version != DX_HASH_LEGACY && + root->info.hash_version != DX_HASH_SIPHASH) { ext4_warning_inode(dir, "Unrecognised inode hash code %u", root->info.hash_version); goto fail; } + if (ext4_hash_in_dirent(dir)) { + if (root->info.hash_version != DX_HASH_SIPHASH) { + ext4_warning_inode(dir, + "Hash in dirent, but hash is not SIPHASH"); + goto fail; + } + } else { + if (root->info.hash_version == DX_HASH_SIPHASH) { + ext4_warning_inode(dir, + "Hash code is SIPHASH, but hash not in dirent"); + goto fail; + } + } if (fname) hinfo = &fname->hinfo; hinfo->hash_version = root->info.hash_version; @@ -989,6 +1010,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, struct ext4_dir_entry_2 *de, *top; int err = 0, count = 0; struct fscrypt_str fname_crypto_str = FSTR_INIT(NULL, 0), tmp_str; + int csum = ext4_has_metadata_csum(dir->i_sb); dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); @@ -997,9 +1019,11 @@ static int htree_dirblock_to_tree(struct file *dir_file, return PTR_ERR(bh); de = (struct ext4_dir_entry_2 *) bh->b_data; + /* csum entries are not larger in the casefolded encrypted case */ top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - - EXT4_DIR_REC_LEN(0)); + ext4_dir_rec_len(0, + csum ? NULL : dir)); #ifdef CONFIG_FS_ENCRYPTION /* Check if the directory is encrypted */ if (IS_ENCRYPTED(dir)) { @@ -1018,13 +1042,23 @@ static int htree_dirblock_to_tree(struct file *dir_file, #endif for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) { if (ext4_check_dir_entry(dir, NULL, de, bh, - bh->b_data, bh->b_size, + bh->b_data, bh->b_size, block, (block<i_sb)) + ((char *)de - bh->b_data))) { /* silently ignore the rest of the block */ break; } - ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + if (ext4_hash_in_dirent(dir)) { + if (de->name_len && de->inode) { + hinfo->hash = EXT4_DIRENT_HASH(de); + hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); + } else { + hinfo->hash = 0; + hinfo->minor_hash = 0; + } + } else { + ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) @@ -1095,7 +1129,11 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, start_hash, start_minor_hash)); dir = file_inode(dir_file); if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) { - hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; + if (ext4_hash_in_dirent(dir)) + hinfo.hash_version = DX_HASH_SIPHASH; + else + hinfo.hash_version = + EXT4_SB(dir->i_sb)->s_def_hash_version; if (hinfo.hash_version <= DX_HASH_TEA) hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; @@ -1188,11 +1226,12 @@ errout: static inline int search_dirblock(struct buffer_head *bh, struct inode *dir, struct ext4_filename *fname, + ext4_lblk_t lblk, unsigned int offset, struct ext4_dir_entry_2 **res_dir) { return ext4_search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir, - fname, offset, res_dir); + fname, lblk, offset, res_dir); } /* @@ -1213,7 +1252,10 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, while ((char *) de < base + blocksize) { if (de->name_len && de->inode) { - ext4fs_dirhash(dir, de->name, de->name_len, &h); + if (ext4_hash_in_dirent(dir)) + h.hash = EXT4_DIRENT_HASH(de); + else + ext4fs_dirhash(dir, de->name, de->name_len, &h); map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; @@ -1277,31 +1319,47 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) * Returns: 0 if the directory entry matches, more than 0 if it * doesn't match or less than zero on error. */ -int ext4_ci_compare(const struct inode *parent, const struct qstr *name, - const struct qstr *entry, bool quick) +static int ext4_ci_compare(const struct inode *parent, const struct qstr *name, + u8 *de_name, size_t de_name_len, bool quick) { const struct super_block *sb = parent->i_sb; const struct unicode_map *um = sb->s_encoding; + struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len); + struct qstr entry = QSTR_INIT(de_name, de_name_len); int ret; - if (quick) - ret = utf8_strncasecmp_folded(um, name, entry); - else - ret = utf8_strncasecmp(um, name, entry); + if (IS_ENCRYPTED(parent)) { + const struct fscrypt_str encrypted_name = + FSTR_INIT(de_name, de_name_len); + decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL); + if (!decrypted_name.name) + return -ENOMEM; + ret = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name, + &decrypted_name); + if (ret < 0) + goto out; + entry.name = decrypted_name.name; + entry.len = decrypted_name.len; + } + + if (quick) + ret = utf8_strncasecmp_folded(um, name, &entry); + else + ret = utf8_strncasecmp(um, name, &entry); if (ret < 0) { /* Handle invalid character sequence as either an error * or as an opaque byte sequence. */ if (sb_has_enc_strict_mode(sb)) - return -EINVAL; - - if (name->len != entry->len) - return 1; - - return !!memcmp(name->name, entry->name, name->len); + ret = -EINVAL; + else if (name->len != entry.len) + ret = 1; + else + ret = !!memcmp(name->name, entry.name, entry.len); } - +out: + kfree(decrypted_name.name); return ret; } @@ -1337,14 +1395,11 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, * * Return: %true if the directory entry matches, otherwise %false. */ -static inline bool ext4_match(const struct inode *parent, +static bool ext4_match(struct inode *parent, const struct ext4_filename *fname, - const struct ext4_dir_entry_2 *de) + struct ext4_dir_entry_2 *de) { struct fscrypt_name f; -#ifdef CONFIG_UNICODE - const struct qstr entry = {.name = de->name, .len = de->name_len}; -#endif if (!de->inode) return false; @@ -1360,10 +1415,23 @@ static inline bool ext4_match(const struct inode *parent, if (fname->cf_name.name) { struct qstr cf = {.name = fname->cf_name.name, .len = fname->cf_name.len}; - return !ext4_ci_compare(parent, &cf, &entry, true); + if (IS_ENCRYPTED(parent)) { + struct dx_hash_info hinfo; + + hinfo.hash_version = DX_HASH_SIPHASH; + hinfo.seed = NULL; + ext4fs_dirhash(parent, fname->cf_name.name, + fname_len(fname), &hinfo); + if (hinfo.hash != EXT4_DIRENT_HASH(de) || + hinfo.minor_hash != + EXT4_DIRENT_MINOR_HASH(de)) + return 0; + } + return !ext4_ci_compare(parent, &cf, de->name, + de->name_len, true); } - return !ext4_ci_compare(parent, fname->usr_fname, &entry, - false); + return !ext4_ci_compare(parent, fname->usr_fname, de->name, + de->name_len, false); } #endif @@ -1375,7 +1443,8 @@ static inline bool ext4_match(const struct inode *parent, */ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, struct inode *dir, struct ext4_filename *fname, - unsigned int offset, struct ext4_dir_entry_2 **res_dir) + ext4_lblk_t lblk, unsigned int offset, + struct ext4_dir_entry_2 **res_dir) { struct ext4_dir_entry_2 * de; char * dlimit; @@ -1391,7 +1460,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, /* found a match - just to be sure, do * a full check */ if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) + bh->b_size, lblk, offset)) return -1; *res_dir = de; return 1; @@ -1437,7 +1506,7 @@ static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, static struct buffer_head *__ext4_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, - int *inlined) + int *inlined, ext4_lblk_t *lblk) { struct super_block *sb; struct buffer_head *bh_use[NAMEI_RA_SIZE]; @@ -1461,6 +1530,8 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, int has_inline_data = 1; ret = ext4_find_inline_entry(dir, fname, res_dir, &has_inline_data); + if (lblk) + *lblk = 0; if (has_inline_data) { if (inlined) *inlined = 1; @@ -1479,7 +1550,7 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, goto restart; } if (is_dx(dir)) { - ret = ext4_dx_find_entry(dir, fname, res_dir); + ret = ext4_dx_find_entry(dir, fname, res_dir, lblk); /* * On success, or if the error was file not found, * return. Otherwise, fall back to doing a search the @@ -1544,9 +1615,11 @@ restart: goto cleanup_and_exit; } set_buffer_verified(bh); - i = search_dirblock(bh, dir, fname, + i = search_dirblock(bh, dir, fname, block, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (i == 1) { + if (lblk) + *lblk = block; EXT4_I(dir)->i_dir_start_lookup = block; ret = bh; goto cleanup_and_exit; @@ -1581,7 +1654,7 @@ cleanup_and_exit: static struct buffer_head *ext4_find_entry(struct inode *dir, const struct qstr *d_name, struct ext4_dir_entry_2 **res_dir, - int *inlined) + int *inlined, ext4_lblk_t *lblk) { int err; struct ext4_filename fname; @@ -1593,7 +1666,7 @@ static struct buffer_head *ext4_find_entry(struct inode *dir, if (err) return ERR_PTR(err); - bh = __ext4_find_entry(dir, &fname, res_dir, inlined); + bh = __ext4_find_entry(dir, &fname, res_dir, inlined, lblk); ext4_fname_free_filename(&fname); return bh; @@ -1614,7 +1687,7 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir, if (err) return ERR_PTR(err); - bh = __ext4_find_entry(dir, &fname, res_dir, NULL); + bh = __ext4_find_entry(dir, &fname, res_dir, NULL, NULL); ext4_fname_free_filename(&fname); return bh; @@ -1622,7 +1695,7 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir, static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, - struct ext4_dir_entry_2 **res_dir) + struct ext4_dir_entry_2 **res_dir, ext4_lblk_t *lblk) { struct super_block * sb = dir->i_sb; struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; @@ -1638,11 +1711,13 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, return (struct buffer_head *) frame; do { block = dx_get_block(frame->at); + if (lblk) + *lblk = block; bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) goto errout; - retval = search_dirblock(bh, dir, fname, + retval = search_dirblock(bh, dir, fname, block, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (retval == 1) @@ -1737,7 +1812,7 @@ struct dentry *ext4_get_parent(struct dentry *child) struct ext4_dir_entry_2 * de; struct buffer_head *bh; - bh = ext4_find_entry(d_inode(child), &dotdot, &de, NULL); + bh = ext4_find_entry(d_inode(child), &dotdot, &de, NULL, NULL); if (IS_ERR(bh)) return (struct dentry *) bh; if (!bh) @@ -1759,7 +1834,8 @@ struct dentry *ext4_get_parent(struct dentry *child) * Returns pointer to last entry moved. */ static struct ext4_dir_entry_2 * -dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, +dx_move_dirents(struct inode *dir, char *from, char *to, + struct dx_map_entry *map, int count, unsigned blocksize) { unsigned rec_len = 0; @@ -1767,7 +1843,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, while (count--) { struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + (map->offs<<2)); - rec_len = EXT4_DIR_REC_LEN(de->name_len); + rec_len = ext4_dir_rec_len(de->name_len, dir); + memcpy (to, de, rec_len); ((struct ext4_dir_entry_2 *) to)->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); @@ -1782,7 +1859,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, * Compact each dir entry in the range to the minimal rec_len. * Returns pointer to last entry in range. */ -static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize) +static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base, + unsigned int blocksize) { struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base; unsigned rec_len = 0; @@ -1791,7 +1869,7 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize) while ((char*)de < base + blocksize) { next = ext4_next_entry(de, blocksize); if (de->inode && de->name_len) { - rec_len = EXT4_DIR_REC_LEN(de->name_len); + rec_len = ext4_dir_rec_len(de->name_len, dir); if (de > to) memmove(to, de, rec_len); to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); @@ -1809,13 +1887,12 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize) * Returns pointer to de in block into which the new entry will be inserted. */ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, - struct buffer_head **bh,struct dx_frame *frame, - struct dx_hash_info *hinfo) + struct buffer_head **bh, struct dx_frame *frame, + struct dx_hash_info *hinfo, ext4_lblk_t *newblock) { unsigned blocksize = dir->i_sb->s_blocksize; unsigned count, continued; struct buffer_head *bh2; - ext4_lblk_t newblock; u32 hash2; struct dx_map_entry *map; char *data1 = (*bh)->b_data, *data2; @@ -1828,7 +1905,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); - bh2 = ext4_append(handle, dir, &newblock); + bh2 = ext4_append(handle, dir, newblock); if (IS_ERR(bh2)) { brelse(*bh); *bh = NULL; @@ -1872,9 +1949,9 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, hash2, split, count-split)); /* Fancy dance to stay within two buffers */ - de2 = dx_move_dirents(data1, data2, map + split, count - split, + de2 = dx_move_dirents(dir, data1, data2, map + split, count - split, blocksize); - de = dx_pack_dirents(data1, blocksize); + de = dx_pack_dirents(dir, data1, blocksize); de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - (char *) de, blocksize); @@ -1899,7 +1976,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, swap(*bh, bh2); de = de2; } - dx_insert_block(frame, hash2 + continued, newblock); + dx_insert_block(frame, hash2 + continued, *newblock); err = ext4_handle_dirty_dirent_node(handle, dir, bh2); if (err) goto journal_error; @@ -1919,13 +1996,14 @@ journal_error: } int ext4_find_dest_de(struct inode *dir, struct inode *inode, + ext4_lblk_t lblk, struct buffer_head *bh, void *buf, int buf_size, struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de) { struct ext4_dir_entry_2 *de; - unsigned short reclen = EXT4_DIR_REC_LEN(fname_len(fname)); + unsigned short reclen = ext4_dir_rec_len(fname_len(fname), dir); int nlen, rlen; unsigned int offset = 0; char *top; @@ -1934,11 +2012,11 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, top = buf + buf_size - reclen; while ((char *) de <= top) { if (ext4_check_dir_entry(dir, NULL, de, bh, - buf, buf_size, offset)) + buf, buf_size, lblk, offset)) return -EFSCORRUPTED; if (ext4_match(dir, fname, de)) return -EEXIST; - nlen = EXT4_DIR_REC_LEN(de->name_len); + nlen = ext4_dir_rec_len(de->name_len, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if ((de->inode ? rlen - nlen : rlen) >= reclen) break; @@ -1952,7 +2030,8 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, return 0; } -void ext4_insert_dentry(struct inode *inode, +void ext4_insert_dentry(struct inode *dir, + struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, struct ext4_filename *fname) @@ -1960,7 +2039,7 @@ void ext4_insert_dentry(struct inode *inode, int nlen, rlen; - nlen = EXT4_DIR_REC_LEN(de->name_len); + nlen = ext4_dir_rec_len(de->name_len, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if (de->inode) { struct ext4_dir_entry_2 *de1 = @@ -1974,6 +2053,17 @@ void ext4_insert_dentry(struct inode *inode, ext4_set_de_type(inode->i_sb, de, inode->i_mode); de->name_len = fname_len(fname); memcpy(de->name, fname_name(fname), fname_len(fname)); + if (ext4_hash_in_dirent(dir)) { + struct dx_hash_info hinfo; + + hinfo.hash_version = DX_HASH_SIPHASH; + hinfo.seed = NULL; + ext4fs_dirhash(dir, fname_usr_name(fname), + fname_len(fname), &hinfo); + EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo.hash); + EXT4_DIRENT_HASHES(de)->minor_hash = + cpu_to_le32(hinfo.minor_hash); + } } /* @@ -1987,6 +2077,7 @@ void ext4_insert_dentry(struct inode *inode, static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, + ext4_lblk_t blk, struct buffer_head *bh) { unsigned int blocksize = dir->i_sb->s_blocksize; @@ -1997,7 +2088,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, csum_size = sizeof(struct ext4_dir_entry_tail); if (!de) { - err = ext4_find_dest_de(dir, inode, bh, bh->b_data, + err = ext4_find_dest_de(dir, inode, blk, bh, bh->b_data, blocksize - csum_size, fname, &de); if (err) return err; @@ -2010,7 +2101,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, } /* By now the buffer is marked for journaling */ - ext4_insert_dentry(inode, de, blocksize, fname); + ext4_insert_dentry(dir, inode, de, blocksize, fname); /* * XXX shouldn't update any times until successful @@ -2106,11 +2197,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, /* Initialize the root; the dot dirents already exist */ de = (struct ext4_dir_entry_2 *) (&root->dotdot); - de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(2), - blocksize); + de->rec_len = ext4_rec_len_to_disk( + blocksize - ext4_dir_rec_len(2, NULL), blocksize); memset (&root->info, 0, sizeof(root->info)); root->info.info_length = sizeof(root->info); - root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; + if (ext4_hash_in_dirent(dir)) + root->info.hash_version = DX_HASH_SIPHASH; + else + root->info.hash_version = + EXT4_SB(dir->i_sb)->s_def_hash_version; + entries = root->entries; dx_set_block(entries, 1); dx_set_count(entries, 1); @@ -2121,7 +2217,12 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, if (fname->hinfo.hash_version <= DX_HASH_TEA) fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; - ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), &fname->hinfo); + if (ext4_hash_in_dirent(dir)) + ext4fs_dirhash(dir, fname_usr_name(fname), + fname_len(fname), &fname->hinfo); + else + ext4fs_dirhash(dir, fname_name(fname), + fname_len(fname), &fname->hinfo); memset(frames, 0, sizeof(frames)); frame = frames; @@ -2136,13 +2237,13 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, if (retval) goto out_frames; - de = do_split(handle,dir, &bh2, frame, &fname->hinfo); + de = do_split(handle, dir, &bh2, frame, &fname->hinfo, &block); if (IS_ERR(de)) { retval = PTR_ERR(de); goto out_frames; } - retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh2); + retval = add_dirent_to_buf(handle, fname, dir, inode, de, block, bh2); out_frames: /* * Even if the block split failed, we have to properly write @@ -2238,7 +2339,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, goto out; } retval = add_dirent_to_buf(handle, &fname, dir, inode, - NULL, bh); + NULL, block, bh); if (retval != -ENOSPC) goto out; @@ -2267,7 +2368,7 @@ add_to_new_block: initialize_dirent_tail(t, blocksize); } - retval = add_dirent_to_buf(handle, &fname, dir, inode, de, bh); + retval = add_dirent_to_buf(handle, &fname, dir, inode, de, block, bh); out: ext4_fname_free_filename(&fname); brelse(bh); @@ -2289,6 +2390,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct ext4_dir_entry_2 *de; int restart; int err; + ext4_lblk_t lblk; again: restart = 0; @@ -2297,7 +2399,8 @@ again: return PTR_ERR(frame); entries = frame->entries; at = frame->at; - bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT_HTREE); + lblk = dx_get_block(frame->at); + bh = ext4_read_dirblock(dir, lblk, DIRENT_HTREE); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; @@ -2309,7 +2412,7 @@ again: if (err) goto journal_error; - err = add_dirent_to_buf(handle, fname, dir, inode, NULL, bh); + err = add_dirent_to_buf(handle, fname, dir, inode, NULL, lblk, bh); if (err != -ENOSPC) goto cleanup; @@ -2429,12 +2532,12 @@ again: goto journal_error; } } - de = do_split(handle, dir, &bh, frame, &fname->hinfo); + de = do_split(handle, dir, &bh, frame, &fname->hinfo, &lblk); if (IS_ERR(de)) { err = PTR_ERR(de); goto cleanup; } - err = add_dirent_to_buf(handle, fname, dir, inode, de, bh); + err = add_dirent_to_buf(handle, fname, dir, inode, de, lblk, bh); goto cleanup; journal_error: @@ -2457,6 +2560,7 @@ cleanup: int ext4_generic_delete_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, + ext4_lblk_t lblk, struct buffer_head *bh, void *entry_buf, int buf_size, @@ -2471,7 +2575,7 @@ int ext4_generic_delete_entry(handle_t *handle, de = (struct ext4_dir_entry_2 *)entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, - bh->b_data, bh->b_size, i)) + bh->b_data, bh->b_size, lblk, i)) return -EFSCORRUPTED; if (de == de_del) { if (pde) @@ -2496,6 +2600,7 @@ int ext4_generic_delete_entry(handle_t *handle, static int ext4_delete_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, + ext4_lblk_t lblk, struct buffer_head *bh) { int err, csum_size = 0; @@ -2516,7 +2621,7 @@ static int ext4_delete_entry(handle_t *handle, if (unlikely(err)) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, + err = ext4_generic_delete_entry(handle, dir, de_del, lblk, bh, bh->b_data, dir->i_sb->s_blocksize, csum_size); if (err) @@ -2699,7 +2804,7 @@ struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, { de->inode = cpu_to_le32(inode->i_ino); de->name_len = 1; - de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len), + de->rec_len = ext4_rec_len_to_disk(ext4_dir_rec_len(de->name_len, NULL), blocksize); strcpy(de->name, "."); ext4_set_de_type(inode->i_sb, de, S_IFDIR); @@ -2709,11 +2814,12 @@ struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, de->name_len = 2; if (!dotdot_real_len) de->rec_len = ext4_rec_len_to_disk(blocksize - - (csum_size + EXT4_DIR_REC_LEN(1)), + (csum_size + ext4_dir_rec_len(1, NULL)), blocksize); else de->rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(de->name_len), blocksize); + ext4_dir_rec_len(de->name_len, NULL), + blocksize); strcpy(de->name, ".."); ext4_set_de_type(inode->i_sb, de, S_IFDIR); @@ -2841,7 +2947,8 @@ bool ext4_empty_dir(struct inode *inode) } sb = inode->i_sb; - if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2)) { + if (inode->i_size < ext4_dir_rec_len(1, NULL) + + ext4_dir_rec_len(2, NULL)) { EXT4_ERROR_INODE(inode, "invalid size"); return true; } @@ -2853,7 +2960,7 @@ bool ext4_empty_dir(struct inode *inode) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; - if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, 0, 0) || le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) { ext4_warning_inode(inode, "directory missing '.'"); @@ -2862,7 +2969,7 @@ bool ext4_empty_dir(struct inode *inode) } offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); de = ext4_next_entry(de, sb->s_blocksize); - if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, 0, offset) || le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { ext4_warning_inode(inode, "directory missing '..'"); @@ -2886,7 +2993,7 @@ bool ext4_empty_dir(struct inode *inode) de = (struct ext4_dir_entry_2 *) (bh->b_data + (offset & (sb->s_blocksize - 1))); if (ext4_check_dir_entry(inode, NULL, de, bh, - bh->b_data, bh->b_size, offset)) { + bh->b_data, bh->b_size, 0, offset)) { offset = (offset | (sb->s_blocksize - 1)) + 1; continue; } @@ -3081,6 +3188,8 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) struct buffer_head *bh; struct ext4_dir_entry_2 *de; handle_t *handle = NULL; + ext4_lblk_t lblk; + if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) return -EIO; @@ -3095,7 +3204,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) return retval; retval = -ENOENT; - bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); + bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL, &lblk); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) @@ -3122,7 +3231,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - retval = ext4_delete_entry(handle, dir, de, bh); + retval = ext4_delete_entry(handle, dir, de, lblk, bh); if (retval) goto end_rmdir; if (!EXT4_DIR_LINK_EMPTY(inode)) @@ -3168,6 +3277,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) struct buffer_head *bh; struct ext4_dir_entry_2 *de; handle_t *handle = NULL; + ext4_lblk_t lblk; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) return -EIO; @@ -3183,7 +3293,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) return retval; retval = -ENOENT; - bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); + bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL, &lblk); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) @@ -3206,7 +3316,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - retval = ext4_delete_entry(handle, dir, de, bh); + retval = ext4_delete_entry(handle, dir, de, lblk, bh); if (retval) goto end_unlink; dir->i_ctime = dir->i_mtime = current_time(dir); @@ -3468,6 +3578,7 @@ struct ext4_renament { int dir_nlink_delta; /* entry for "dentry" */ + ext4_lblk_t lblk; struct buffer_head *bh; struct ext4_dir_entry_2 *de; int inlined; @@ -3557,12 +3668,13 @@ static int ext4_find_delete_entry(handle_t *handle, struct inode *dir, int retval = -ENOENT; struct buffer_head *bh; struct ext4_dir_entry_2 *de; + ext4_lblk_t lblk; - bh = ext4_find_entry(dir, d_name, &de, NULL); + bh = ext4_find_entry(dir, d_name, &de, NULL, &lblk); if (IS_ERR(bh)) return PTR_ERR(bh); if (bh) { - retval = ext4_delete_entry(handle, dir, de, bh); + retval = ext4_delete_entry(handle, dir, de, lblk, bh); brelse(bh); } return retval; @@ -3586,7 +3698,8 @@ static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent, retval = ext4_find_delete_entry(handle, ent->dir, &ent->dentry->d_name); } else { - retval = ext4_delete_entry(handle, ent->dir, ent->de, ent->bh); + retval = ext4_delete_entry(handle, ent->dir, ent->de, + ent->lblk, ent->bh); if (retval == -ENOENT) { retval = ext4_find_delete_entry(handle, ent->dir, &ent->dentry->d_name); @@ -3699,7 +3812,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, return retval; } - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL, + &old.lblk); if (IS_ERR(old.bh)) return PTR_ERR(old.bh); /* @@ -3713,7 +3827,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; new.bh = ext4_find_entry(new.dir, &new.dentry->d_name, - &new.de, &new.inlined); + &new.de, &new.inlined, NULL); if (IS_ERR(new.bh)) { retval = PTR_ERR(new.bh); new.bh = NULL; @@ -3893,7 +4007,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, return retval; old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, - &old.de, &old.inlined); + &old.de, &old.inlined, NULL); if (IS_ERR(old.bh)) return PTR_ERR(old.bh); /* @@ -3907,7 +4021,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; new.bh = ext4_find_entry(new.dir, &new.dentry->d_name, - &new.de, &new.inlined); + &new.de, &new.inlined, NULL); if (IS_ERR(new.bh)) { retval = PTR_ERR(new.bh); new.bh = NULL; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b04043718930..4d1aae380afb 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3882,12 +3882,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) struct unicode_map *encoding; __u16 encoding_flags; - if (ext4_has_feature_encrypt(sb)) { - ext4_msg(sb, KERN_ERR, - "Can't mount with encoding and encryption"); - goto failed_mount; - } - if (ext4_sb_read_encoding(es, &encoding_info, &encoding_flags)) { ext4_msg(sb, KERN_ERR, From 6ccc4309743b5cd821584d30fc971dd375bb976c Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 6 Nov 2019 17:00:25 -0800 Subject: [PATCH 022/162] ANDROID: ext4: Optimize match for casefolded encrypted dirs Matching names with casefolded encrypting directories requires decrypting entries to confirm case since we are case preserving. We can avoid needing to decrypt if our hash values don't match. Signed-off-by: Daniel Rosenberg Test: Boots, /data/media is case insensitive Bug: 138322712 Change-Id: Id6024fc2a3bbde1e46a29070981fa64b3f667075 --- fs/ext4/ext4.h | 17 ++++++++-------- fs/ext4/namei.c | 53 ++++++++++++++++++++++++++----------------------- 2 files changed, 37 insertions(+), 33 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 81a42aa9c764..1e71fb42a841 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2405,9 +2405,9 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); #ifdef CONFIG_UNICODE -extern void ext4_fname_setup_ci_filename(struct inode *dir, +extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, - struct fscrypt_str *fname); + struct ext4_filename *fname); #endif #ifdef CONFIG_FS_ENCRYPTION @@ -2438,9 +2438,9 @@ static inline int ext4_fname_setup_filename(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); #ifdef CONFIG_UNICODE - ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); + err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif - return 0; + return err; } static inline int ext4_fname_prepare_lookup(struct inode *dir, @@ -2457,9 +2457,9 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); #ifdef CONFIG_UNICODE - ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name); + err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); #endif - return 0; + return err; } static inline void ext4_fname_free_filename(struct ext4_filename *fname) @@ -2484,15 +2484,16 @@ static inline int ext4_fname_setup_filename(struct inode *dir, int lookup, struct ext4_filename *fname) { + int err = 0; fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; #ifdef CONFIG_UNICODE - ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); + err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif - return 0; + return err; } static inline int ext4_fname_prepare_lookup(struct inode *dir, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a5cc430173f9..650f0ef14fcc 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -795,7 +795,9 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, if (hinfo->hash_version <= DX_HASH_TEA) hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; - if (fname && fname_name(fname)) + /* hash is already computed for encrypted casefolded directory */ + if (fname && fname_name(fname) && + !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo); hash = hinfo->hash; @@ -1363,19 +1365,21 @@ out: return ret; } -void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, - struct fscrypt_str *cf_name) +int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, + struct ext4_filename *name) { + struct fscrypt_str *cf_name = &name->cf_name; + struct dx_hash_info *hinfo = &name->hinfo; int len; if (!needs_casefold(dir)) { cf_name->name = NULL; - return; + return 0; } cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS); if (!cf_name->name) - return; + return -ENOMEM; len = utf8_casefold(dir->i_sb->s_encoding, iname, cf_name->name, @@ -1383,10 +1387,18 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, if (len <= 0) { kfree(cf_name->name); cf_name->name = NULL; - return; } cf_name->len = (unsigned) len; + if (!IS_ENCRYPTED(dir)) + return 0; + hinfo->hash_version = DX_HASH_SIPHASH; + hinfo->seed = NULL; + if (cf_name->name) + ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo); + else + ext4fs_dirhash(dir, iname->name, iname->len, hinfo); + return 0; } #endif @@ -1416,16 +1428,12 @@ static bool ext4_match(struct inode *parent, struct qstr cf = {.name = fname->cf_name.name, .len = fname->cf_name.len}; if (IS_ENCRYPTED(parent)) { - struct dx_hash_info hinfo; + if (fname->hinfo.hash != EXT4_DIRENT_HASH(de) || + fname->hinfo.minor_hash != + EXT4_DIRENT_MINOR_HASH(de)) { - hinfo.hash_version = DX_HASH_SIPHASH; - hinfo.seed = NULL; - ext4fs_dirhash(parent, fname->cf_name.name, - fname_len(fname), &hinfo); - if (hinfo.hash != EXT4_DIRENT_HASH(de) || - hinfo.minor_hash != - EXT4_DIRENT_MINOR_HASH(de)) return 0; + } } return !ext4_ci_compare(parent, &cf, de->name, de->name_len, true); @@ -2054,15 +2062,11 @@ void ext4_insert_dentry(struct inode *dir, de->name_len = fname_len(fname); memcpy(de->name, fname_name(fname), fname_len(fname)); if (ext4_hash_in_dirent(dir)) { - struct dx_hash_info hinfo; + struct dx_hash_info *hinfo = &fname->hinfo; - hinfo.hash_version = DX_HASH_SIPHASH; - hinfo.seed = NULL; - ext4fs_dirhash(dir, fname_usr_name(fname), - fname_len(fname), &hinfo); - EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo.hash); + EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo->hash); EXT4_DIRENT_HASHES(de)->minor_hash = - cpu_to_le32(hinfo.minor_hash); + cpu_to_le32(hinfo->minor_hash); } } @@ -2217,10 +2221,9 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, if (fname->hinfo.hash_version <= DX_HASH_TEA) fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; - if (ext4_hash_in_dirent(dir)) - ext4fs_dirhash(dir, fname_usr_name(fname), - fname_len(fname), &fname->hinfo); - else + + /* casefolded encrypted hashes are computed on fname setup */ + if (!ext4_hash_in_dirent(dir)) ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), &fname->hinfo); From 5f8d359e8657eca76a8139cd97267a99fa87a0d6 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Tue, 2 Jun 2020 21:00:51 +0300 Subject: [PATCH 023/162] s390: fix syscall_get_error for compat processes commit b3583fca5fb654af2cfc1c08259abb9728272538 upstream. If both the tracer and the tracee are compat processes, and gprs[2] is assigned a value by __poke_user_compat, then the higher 32 bits of gprs[2] are cleared, IS_ERR_VALUE() always returns false, and syscall_get_error() always returns 0. Fix the implementation by sign-extending the value for compat processes the same way as x86 implementation does. The bug was exposed to user space by commit 201766a20e30f ("ptrace: add PTRACE_GET_SYSCALL_INFO request") and detected by strace test suite. This change fixes strace syscall tampering on s390. Link: https://lkml.kernel.org/r/20200602180051.GA2427@altlinux.org Fixes: 753c4dd6a2fa2 ("[S390] ptrace changes") Cc: Elvira Khabirova Cc: stable@vger.kernel.org # v2.6.28+ Signed-off-by: Dmitry V. Levin Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Greg Kroah-Hartman --- arch/s390/include/asm/syscall.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 6bc941be6921..166fbd74e316 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -41,7 +41,17 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0; + unsigned long error = regs->gprs[2]; +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_31BIT)) { + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + error = (long)(int)error; + } +#endif + return IS_ERR_VALUE(error) ? error : 0; } static inline long syscall_get_return_value(struct task_struct *task, From 9b91163f97f98fedfffe1d81732ecfe21cc13a79 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 1 Jun 2020 17:19:42 +0100 Subject: [PATCH 024/162] drm/i915: Whitelist context-local timestamp in the gen9 cmdparser commit 273500ae71711c040d258a7b3f4b6f44c368fff2 upstream. Allow batch buffers to read their own _local_ cumulative HW runtime of their logical context. Fixes: 0f2f39758341 ("drm/i915: Add gen9 BCS cmdparsing") Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: # v5.4+ Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20200601161942.30854-1-chris@chris-wilson.co.uk (cherry picked from commit f9496520df11de00fbafc3cbd693b9570d600ab3) Signed-off-by: Joonas Lahtinen Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index e4b9eb1f6b60..f6b81f3256cf 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -570,6 +570,9 @@ struct drm_i915_reg_descriptor { #define REG32(_reg, ...) \ { .addr = (_reg), __VA_ARGS__ } +#define REG32_IDX(_reg, idx) \ + { .addr = _reg(idx) } + /* * Convenience macro for adding 64-bit registers. * @@ -667,6 +670,7 @@ static const struct drm_i915_reg_descriptor gen9_blt_regs[] = { REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE), REG32(BCS_SWCTRL), REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), + REG32_IDX(RING_CTX_TIMESTAMP, BLT_RING_BASE), REG64_IDX(BCS_GPR, 0), REG64_IDX(BCS_GPR, 1), REG64_IDX(BCS_GPR, 2), From 04b007182932d0dae4ce3622d2e214bac0ec1a60 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 13 Apr 2020 16:10:51 +0200 Subject: [PATCH 025/162] power: supply: bq24257_charger: Replace depends on REGMAP_I2C with select [ Upstream commit 87c3d579c8ed0eaea6b1567d529a8daa85a2bc6c ] regmap is a library function that gets selected by drivers that need it. No driver modules should depend on it. Depending on REGMAP_I2C makes this driver only build if another driver already selected REGMAP_I2C, as the symbol can't be selected through the menu kernel configuration. Fixes: 2219a935963e ("power_supply: Add TI BQ24257 charger driver") Signed-off-by: Enric Balletbo i Serra Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index 5ab90c1f3f7c..24163cf8612c 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -530,7 +530,7 @@ config CHARGER_BQ24257 tristate "TI BQ24250/24251/24257 battery charger driver" depends on I2C depends on GPIOLIB || COMPILE_TEST - depends on REGMAP_I2C + select REGMAP_I2C help Say Y to enable support for the TI BQ24250, BQ24251, and BQ24257 battery chargers. From 2d43a469e439adb8e22af18e204bc7aa164e43d4 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Tue, 17 Mar 2020 22:13:32 +0100 Subject: [PATCH 026/162] clk: sunxi: Fix incorrect usage of round_down() [ Upstream commit ee25d9742dabed3fd18158b518f846abeb70f319 ] round_down() can only round to powers of 2. If round_down() is asked to round to something that is not a power of 2, incorrect results are produced. The incorrect results can be both too large and too small. Instead, use rounddown() which can round to any number. Fixes: 6a721db180a2 ("clk: sunxi: Add A31 clocks support") Signed-off-by: Rikard Falkeborn Signed-off-by: Maxime Ripard Signed-off-by: Sasha Levin --- drivers/clk/sunxi/clk-sunxi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c index aa4add580516..0b5e091742f9 100644 --- a/drivers/clk/sunxi/clk-sunxi.c +++ b/drivers/clk/sunxi/clk-sunxi.c @@ -98,7 +98,7 @@ static void sun6i_a31_get_pll1_factors(struct factors_request *req) * Round down the frequency to the closest multiple of either * 6 or 16 */ - u32 round_freq_6 = round_down(freq_mhz, 6); + u32 round_freq_6 = rounddown(freq_mhz, 6); u32 round_freq_16 = round_down(freq_mhz, 16); if (round_freq_6 > round_freq_16) From 1bf0b66cf37664eeb802383e5d05525e2e5e3706 Mon Sep 17 00:00:00 2001 From: Adam Honse Date: Fri, 10 Apr 2020 15:48:44 -0500 Subject: [PATCH 027/162] i2c: piix4: Detect secondary SMBus controller on AMD AM4 chipsets [ Upstream commit f27237c174fd9653033330e4e532cd9d153ce824 ] The AMD X370 and other AM4 chipsets (A/B/X 3/4/5 parts) and Threadripper equivalents have a secondary SMBus controller at I/O port address 0x0B20. This bus is used by several manufacturers to control motherboard RGB lighting via embedded controllers. I have been using this bus in my OpenRGB project to control the Aura RGB on many motherboards and ASRock also uses this bus for their Polychrome RGB controller. I am not aware of any CZ-compatible platforms which do not have the second SMBus channel. All of AMD's AM4- and Threadripper- series chipsets that OpenRGB users have tested appear to have this secondary bus. I also noticed this secondary bus is present on older AMD platforms including my FM1 home server. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202587 Signed-off-by: Adam Honse Reviewed-by: Jean Delvare Reviewed-by: Sebastian Reichel Tested-by: Sebastian Reichel Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-piix4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 4b81dc231b18..5345b731bb7c 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -960,7 +960,8 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) } if (dev->vendor == PCI_VENDOR_ID_AMD && - dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS) { + (dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS || + dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS)) { retval = piix4_setup_sb800(dev, id, 1); } From 350821de867f31a02ee93bba307c7ec5f3d90df4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 23 Mar 2020 12:41:25 +0200 Subject: [PATCH 028/162] iio: pressure: bmp280: Tolerate IRQ before registering [ Upstream commit 97b31a6f5fb95b1ec6575b78a7240baddba34384 ] With DEBUG_SHIRQ enabled we have a kernel crash [ 116.482696] BUG: kernel NULL pointer dereference, address: 0000000000000000 ... [ 116.606571] Call Trace: [ 116.609023] [ 116.611047] complete+0x34/0x50 [ 116.614206] bmp085_eoc_irq+0x9/0x10 [bmp280] because DEBUG_SHIRQ mechanism fires an IRQ before registration and drivers ought to be able to handle an interrupt happening before request_irq() returns. Fixes: aae953949651 ("iio: pressure: bmp280: add support for BMP085 EOC interrupt") Signed-off-by: Andy Shevchenko Acked-by: Linus Walleij Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/pressure/bmp280-core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 5f625ffa2a88..3204dff34e0a 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -651,7 +651,7 @@ static int bmp180_measure(struct bmp280_data *data, u8 ctrl_meas) unsigned int ctrl; if (data->use_eoc) - init_completion(&data->done); + reinit_completion(&data->done); ret = regmap_write(data->regmap, BMP280_REG_CTRL_MEAS, ctrl_meas); if (ret) @@ -907,6 +907,9 @@ static int bmp085_fetch_eoc_irq(struct device *dev, "trying to enforce it\n"); irq_trig = IRQF_TRIGGER_RISING; } + + init_completion(&data->done); + ret = devm_request_threaded_irq(dev, irq, bmp085_eoc_irq, From 3f0644274003cd7c4087ec104b50b731d5d4fb17 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 15 Apr 2020 14:48:52 -0600 Subject: [PATCH 029/162] remoteproc: Fix IDR initialisation in rproc_alloc() [ Upstream commit 6442df49400b466431979e7634849a464a5f1861 ] If ida_simple_get() returns an error when called in rproc_alloc(), put_device() is called to clean things up. By this time the rproc device type has been assigned, with rproc_type_release() as the release function. The first thing rproc_type_release() does is call: idr_destroy(&rproc->notifyids); But at the time the ida_simple_get() call is made, the notifyids field in the remoteproc structure has not been initialized. I'm not actually sure this case causes an observable problem, but it's incorrect. Fix this by initializing the notifyids field before calling ida_simple_get() in rproc_alloc(). Fixes: b5ab5e24e960 ("remoteproc: maintain a generic child device for each rproc") Signed-off-by: Alex Elder Reviewed-by: Mathieu Poirier Reviewed-by: Suman Anna Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200415204858.2448-2-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/remoteproc/remoteproc_core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 8f4fa1a52f05..d6372470e5be 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1432,6 +1432,7 @@ struct rproc *rproc_alloc(struct device *dev, const char *name, rproc->dev.type = &rproc_type; rproc->dev.class = &rproc_class; rproc->dev.driver_data = rproc; + idr_init(&rproc->notifyids); /* Assign a unique device index and name */ rproc->index = ida_simple_get(&rproc_dev_index, 0, 0, GFP_KERNEL); @@ -1450,8 +1451,6 @@ struct rproc *rproc_alloc(struct device *dev, const char *name, mutex_init(&rproc->lock); - idr_init(&rproc->notifyids); - INIT_LIST_HEAD(&rproc->carveouts); INIT_LIST_HEAD(&rproc->mappings); INIT_LIST_HEAD(&rproc->traces); From 1fc159f96633a50cf83fb220f98feba034e6eff4 Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Sun, 29 Mar 2020 13:41:16 +0100 Subject: [PATCH 030/162] clk: qcom: msm8916: Fix the address location of pll->config_reg [ Upstream commit f47ab3c2f5338828a67e89d5f688d2cef9605245 ] During the process of debugging a processor derived from the msm8916 which we found the new processor was not starting one of its PLLs. After tracing the addresses and writes that downstream was doing and comparing to upstream it became obvious that we were writing to a different register location than downstream when trying to configure the PLL. This error is also present in upstream msm8916. As an example clk-pll.c::clk_pll_recalc_rate wants to write to pll->config_reg updating the bit-field POST_DIV_RATIO. That bit-field is defined in PLL_USER_CTL not in PLL_CONFIG_CTL. Taking the BIMC PLL as an example lm80-p0436-13_c_qc_snapdragon_410_processor_hrd.pdf 0x01823010 GCC_BIMC_PLL_USER_CTL 0x01823014 GCC_BIMC_PLL_CONFIG_CTL This pattern is repeated for gpll0, gpll1, gpll2 and bimc_pll. This error is likely not apparent since the bootloader will already have initialized these PLLs. This patch corrects the location of config_reg from PLL_CONFIG_CTL to PLL_USER_CTL for all relevant PLLs on msm8916. Fixes commit 3966fab8b6ab ("clk: qcom: Add MSM8916 Global Clock Controller support") Cc: Georgi Djakov Cc: Andy Gross Cc: Bjorn Andersson Cc: Michael Turquette Cc: Stephen Boyd Signed-off-by: Bryan O'Donoghue Link: https://lkml.kernel.org/r/20200329124116.4185447-1-bryan.odonoghue@linaro.org Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-msm8916.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c index 2057809219f4..7426d910e079 100644 --- a/drivers/clk/qcom/gcc-msm8916.c +++ b/drivers/clk/qcom/gcc-msm8916.c @@ -270,7 +270,7 @@ static struct clk_pll gpll0 = { .l_reg = 0x21004, .m_reg = 0x21008, .n_reg = 0x2100c, - .config_reg = 0x21014, + .config_reg = 0x21010, .mode_reg = 0x21000, .status_reg = 0x2101c, .status_bit = 17, @@ -297,7 +297,7 @@ static struct clk_pll gpll1 = { .l_reg = 0x20004, .m_reg = 0x20008, .n_reg = 0x2000c, - .config_reg = 0x20014, + .config_reg = 0x20010, .mode_reg = 0x20000, .status_reg = 0x2001c, .status_bit = 17, @@ -324,7 +324,7 @@ static struct clk_pll gpll2 = { .l_reg = 0x4a004, .m_reg = 0x4a008, .n_reg = 0x4a00c, - .config_reg = 0x4a014, + .config_reg = 0x4a010, .mode_reg = 0x4a000, .status_reg = 0x4a01c, .status_bit = 17, @@ -351,7 +351,7 @@ static struct clk_pll bimc_pll = { .l_reg = 0x23004, .m_reg = 0x23008, .n_reg = 0x2300c, - .config_reg = 0x23014, + .config_reg = 0x23010, .mode_reg = 0x23000, .status_reg = 0x2301c, .status_bit = 17, From 7d6960cd97513692c6529430345e7b6b2f5325b5 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Mon, 24 Feb 2020 14:07:48 +0000 Subject: [PATCH 031/162] backlight: lp855x: Ensure regulators are disabled on probe failure [ Upstream commit d8207c155a7c6015eb7f43739baa7dfb1fa638af ] If probing the LP885x backlight fails after the regulators have been enabled, then the following warning is seen when releasing the regulators ... WARNING: CPU: 1 PID: 289 at drivers/regulator/core.c:2051 _regulator_put.part.28+0x158/0x160 Modules linked in: tegra_xudc lp855x_bl(+) host1x pwm_tegra ip_tables x_tables ipv6 nf_defrag_ipv6 CPU: 1 PID: 289 Comm: systemd-udevd Not tainted 5.6.0-rc2-next-20200224 #1 Hardware name: NVIDIA Jetson TX1 Developer Kit (DT) ... Call trace: _regulator_put.part.28+0x158/0x160 regulator_put+0x34/0x50 devm_regulator_release+0x10/0x18 release_nodes+0x12c/0x230 devres_release_all+0x34/0x50 really_probe+0x1c0/0x370 driver_probe_device+0x58/0x100 device_driver_attach+0x6c/0x78 __driver_attach+0xb0/0xf0 bus_for_each_dev+0x68/0xc8 driver_attach+0x20/0x28 bus_add_driver+0x160/0x1f0 driver_register+0x60/0x110 i2c_register_driver+0x40/0x80 lp855x_driver_init+0x20/0x1000 [lp855x_bl] do_one_initcall+0x58/0x1a0 do_init_module+0x54/0x1d0 load_module+0x1d80/0x21c8 __do_sys_finit_module+0xe8/0x100 __arm64_sys_finit_module+0x18/0x20 el0_svc_common.constprop.3+0xb0/0x168 do_el0_svc+0x20/0x98 el0_sync_handler+0xf4/0x1b0 el0_sync+0x140/0x180 Fix this by ensuring that the regulators are disabled, if enabled, on probe failure. Finally, ensure that the vddio regulator is disabled in the driver remove handler. Signed-off-by: Jon Hunter Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/video/backlight/lp855x_bl.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c index 939f057836e1..4cdc7a3f6dc5 100644 --- a/drivers/video/backlight/lp855x_bl.c +++ b/drivers/video/backlight/lp855x_bl.c @@ -460,7 +460,7 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id) ret = regulator_enable(lp->enable); if (ret < 0) { dev_err(lp->dev, "failed to enable vddio: %d\n", ret); - return ret; + goto disable_supply; } /* @@ -475,24 +475,34 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id) ret = lp855x_configure(lp); if (ret) { dev_err(lp->dev, "device config err: %d", ret); - return ret; + goto disable_vddio; } ret = lp855x_backlight_register(lp); if (ret) { dev_err(lp->dev, "failed to register backlight. err: %d\n", ret); - return ret; + goto disable_vddio; } ret = sysfs_create_group(&lp->dev->kobj, &lp855x_attr_group); if (ret) { dev_err(lp->dev, "failed to register sysfs. err: %d\n", ret); - return ret; + goto disable_vddio; } backlight_update_status(lp->bl); + return 0; + +disable_vddio: + if (lp->enable) + regulator_disable(lp->enable); +disable_supply: + if (lp->supply) + regulator_disable(lp->supply); + + return ret; } static int lp855x_remove(struct i2c_client *cl) @@ -501,6 +511,8 @@ static int lp855x_remove(struct i2c_client *cl) lp->bl->props.brightness = 0; backlight_update_status(lp->bl); + if (lp->enable) + regulator_disable(lp->enable); if (lp->supply) regulator_disable(lp->supply); sysfs_remove_group(&lp->dev->kobj, &lp855x_attr_group); From c36fc307b7ba6f8f4619867b522d77141e6f116d Mon Sep 17 00:00:00 2001 From: Xiyu Yang Date: Sat, 25 Apr 2020 20:48:35 +0800 Subject: [PATCH 032/162] ASoC: davinci-mcasp: Fix dma_chan refcnt leak when getting dma type [ Upstream commit a697ae6ea56e23397341b027098c1b11d9ab13da ] davinci_mcasp_get_dma_type() invokes dma_request_chan(), which returns a reference of the specified dma_chan object to "chan" with increased refcnt. When davinci_mcasp_get_dma_type() returns, local variable "chan" becomes invalid, so the refcount should be decreased to keep refcount balanced. The reference counting issue happens in one exception handling path of davinci_mcasp_get_dma_type(). When chan device is NULL, the function forgets to decrease the refcnt increased by dma_request_chan(), causing a refcnt leak. Fix this issue by calling dma_release_channel() when chan device is NULL. Signed-off-by: Xiyu Yang Signed-off-by: Xin Tan Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/r/1587818916-38730-1-git-send-email-xiyuyang19@fudan.edu.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/davinci/davinci-mcasp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index e10e03800cce..6991718d7c8a 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -1747,8 +1747,10 @@ static int davinci_mcasp_get_dma_type(struct davinci_mcasp *mcasp) PTR_ERR(chan)); return PTR_ERR(chan); } - if (WARN_ON(!chan->device || !chan->device->dev)) + if (WARN_ON(!chan->device || !chan->device->dev)) { + dma_release_channel(chan); return -EINVAL; + } if (chan->device->dev->of_node) ret = of_property_read_string(chan->device->dev->of_node, From 33ce3576d1a594065437d3f86f6137b8f111303e Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 13 Feb 2020 15:27:54 +0100 Subject: [PATCH 033/162] ARM: integrator: Add some Kconfig selections [ Upstream commit d2854bbe5f5c4b4bec8061caf4f2e603d8819446 ] The CMA and DMA_CMA Kconfig options need to be selected by the Integrator in order to produce boot console on some Integrator systems. The REGULATOR and REGULATOR_FIXED_VOLTAGE need to be selected in order to boot the system from an external MMC card when using MMCI/PL181 from the device tree probe path. Select these things directly from the Kconfig so we are sure to be able to bring the systems up with console from any device tree. Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- arch/arm/mach-integrator/Kconfig | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig index cefe44f6889b..ba124f8704fa 100644 --- a/arch/arm/mach-integrator/Kconfig +++ b/arch/arm/mach-integrator/Kconfig @@ -3,6 +3,8 @@ menuconfig ARCH_INTEGRATOR depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V6 select ARM_AMBA select COMMON_CLK_VERSATILE + select CMA + select DMA_CMA select HAVE_TCM select ICST select MFD_SYSCON @@ -34,14 +36,13 @@ config INTEGRATOR_IMPD1 select ARM_VIC select GPIO_PL061 select GPIOLIB + select REGULATOR + select REGULATOR_FIXED_VOLTAGE help The IM-PD1 is an add-on logic module for the Integrator which allows ARM(R) Ltd PrimeCells to be developed and evaluated. The IM-PD1 can be found on the Integrator/PP2 platform. - To compile this driver as a module, choose M here: the - module will be called impd1. - config INTEGRATOR_CM7TDMI bool "Integrator/CM7TDMI core module" depends on ARCH_INTEGRATOR_AP From d013955da9894070aae278a4ab24f8b72df6aa43 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 28 Apr 2020 16:19:39 +0300 Subject: [PATCH 034/162] scsi: qedi: Check for buffer overflow in qedi_set_path() [ Upstream commit 4a4c0cfb4be74e216dd4446b254594707455bfc6 ] Smatch complains that the "path_data->handle" variable is user controlled. It comes from iscsi_set_path() so that seems possible. It's harmless to add a limit check. The qedi->ep_tbl[] array has qedi->max_active_conns elements (which is always ISCSI_MAX_SESS_PER_HBA (4096) elements). The array is allocated in the qedi_cm_alloc_mem() function. Link: https://lore.kernel.org/r/20200428131939.GA696531@mwanda Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.") Acked-by: Manish Rangankar Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedi/qedi_iscsi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 94f3829b1974..1effac1111d5 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -1224,6 +1224,10 @@ static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) } iscsi_cid = (u32)path_data->handle; + if (iscsi_cid >= qedi->max_active_conns) { + ret = -EINVAL; + goto set_path_exit; + } qedi_ep = qedi->ep_tbl[iscsi_cid]; QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "iscsi_cid=0x%x, qedi_ep=%p\n", iscsi_cid, qedi_ep); From cd202586d160a862a70ea615d05a2dc64550995a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 1 May 2020 12:40:11 +0300 Subject: [PATCH 035/162] ALSA: isa/wavefront: prevent out of bounds write in ioctl [ Upstream commit 7f0d5053c5a9d23fe5c2d337495a9d79038d267b ] The "header->number" comes from the ioctl and it needs to be clamped to prevent out of bounds writes. Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20200501094011.GA960082@mwanda Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/isa/wavefront/wavefront_synth.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c index 0b1e4b34b299..13c8e6542a2f 100644 --- a/sound/isa/wavefront/wavefront_synth.c +++ b/sound/isa/wavefront/wavefront_synth.c @@ -1175,7 +1175,10 @@ wavefront_send_alias (snd_wavefront_t *dev, wavefront_patch_info *header) "alias for %d\n", header->number, header->hdr.a.OriginalSample); - + + if (header->number >= WF_MAX_SAMPLE) + return -EINVAL; + munge_int32 (header->number, &alias_hdr[0], 2); munge_int32 (header->hdr.a.OriginalSample, &alias_hdr[2], 2); munge_int32 (*((unsigned int *)&header->hdr.a.sampleStartOffset), @@ -1206,6 +1209,9 @@ wavefront_send_multisample (snd_wavefront_t *dev, wavefront_patch_info *header) int num_samples; unsigned char *msample_hdr; + if (header->number >= WF_MAX_SAMPLE) + return -EINVAL; + msample_hdr = kmalloc(WF_MSAMPLE_BYTES, GFP_KERNEL); if (! msample_hdr) return -ENOMEM; From 2966b022f98fe102d38386f3d33deaed508a4d05 Mon Sep 17 00:00:00 2001 From: Viacheslav Dubeyko Date: Wed, 22 Apr 2020 13:55:52 +0300 Subject: [PATCH 036/162] scsi: qla2xxx: Fix issue with adapter's stopping state [ Upstream commit 803e45550b11c8e43d89812356fe6f105adebdf9 ] The goal of the following command sequence is to restart the adapter. However, the tgt_stop flag remains set, indicating that the adapter is still in stopping state even after re-enabling it. echo 0x7fffffff > /sys/module/qla2xxx/parameters/logging modprobe target_core_mod modprobe tcm_qla2xxx mkdir /sys/kernel/config/target/qla2xxx mkdir /sys/kernel/config/target/qla2xxx/ mkdir /sys/kernel/config/target/qla2xxx//tpgt_1 echo 1 > /sys/kernel/config/target/qla2xxx//tpgt_1/enable echo 0 > /sys/kernel/config/target/qla2xxx//tpgt_1/enable echo 1 > /sys/kernel/config/target/qla2xxx//tpgt_1/enable kernel: PID 1396:qla_target.c:1555 qlt_stop_phase1(): tgt_stop 0x0, tgt_stopped 0x0 kernel: qla2xxx [0001:00:02.0]-e803:1: PID 1396:qla_target.c:1567: Stopping target for host 1(c0000000033557e8) kernel: PID 1396:qla_target.c:1579 qlt_stop_phase1(): tgt_stop 0x1, tgt_stopped 0x0 kernel: PID 1396:qla_target.c:1266 qlt_schedule_sess_for_deletion(): tgt_stop 0x1, tgt_stopped 0x0 kernel: qla2xxx [0001:00:02.0]-e801:1: PID 1396:qla_target.c:1316: Scheduling sess c00000002d5cd800 for deletion 21:00:00:24:ff:7f:35:c7 kernel: qla2xxx [0001:00:02.0]-290a:1: PID 340:qla_target.c:1187: qlt_unreg_sess sess c00000002d5cd800 for deletion 21:00:00:24:ff:7f:35:c7 kernel: qla2xxx [0001:00:02.0]-f801:1: PID 340:qla_target.c:1145: Unregistration of sess c00000002d5cd800 21:00:00:24:ff:7f:35:c7 finished fcp_cnt 0 kernel: PID 340:qla_target.c:1155 qlt_free_session_done(): tgt_stop 0x1, tgt_stopped 0x0 kernel: qla2xxx [0001:00:02.0]-4807:1: PID 346:qla_os.c:6329: ISP abort scheduled. kernel: qla2xxx [0001:00:02.0]-28f1:1: PID 346:qla_os.c:3956: Mark all dev lost kernel: PID 346:qla_target.c:1266 qlt_schedule_sess_for_deletion(): tgt_stop 0x1, tgt_stopped 0x0 kernel: qla2xxx [0001:00:02.0]-4808:1: PID 346:qla_os.c:6338: ISP abort end. kernel: PID 1396:qla_target.c:6812 qlt_enable_vha(): tgt_stop 0x1, tgt_stopped 0x0 kernel: qla2xxx [0001:00:02.0]-4807:1: PID 346:qla_os.c:6329: ISP abort scheduled. kernel: qla2xxx [0001:00:02.0]-4808:1: PID 346:qla_os.c:6338: ISP abort end. qlt_handle_cmd_for_atio() rejects the request to send commands because the adapter is in the stopping state: kernel: PID 0:qla_target.c:4442 qlt_handle_cmd_for_atio(): tgt_stop 0x1, tgt_stopped 0x0 kernel: qla2xxx [0001:00:02.0]-3861:1: PID 0:qla_target.c:4447: New command while device c000000005314600 is shutting down kernel: qla2xxx [0001:00:02.0]-e85f:1: PID 0:qla_target.c:5728: qla_target: Unable to send command to target This patch calls qla_stop_phase2() in addition to qlt_stop_phase1() in tcm_qla2xxx_tpg_enable_store() and tcm_qla2xxx_npiv_tpg_enable_store(). The qlt_stop_phase1() marks adapter as stopping (tgt_stop == 0x1, tgt_stopped == 0x0) but qlt_stop_phase2() marks adapter as stopped (tgt_stop == 0x0, tgt_stopped == 0x1). Link: https://lore.kernel.org/r/52be1e8a3537f6c5407eae3edd4c8e08a9545ea5.camel@yadro.com Reviewed-by: Roman Bolshakov Reviewed-by: Himanshu Madhani Signed-off-by: Viacheslav Dubeyko Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index e08ac431bc49..e7aee067b056 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -937,6 +937,7 @@ static ssize_t tcm_qla2xxx_tpg_enable_store(struct config_item *item, atomic_set(&tpg->lport_tpg_enabled, 0); qlt_stop_phase1(vha->vha_tgt.qla_tgt); + qlt_stop_phase2(vha->vha_tgt.qla_tgt); } return count; @@ -1101,6 +1102,7 @@ static ssize_t tcm_qla2xxx_npiv_tpg_enable_store(struct config_item *item, atomic_set(&tpg->lport_tpg_enabled, 0); qlt_stop_phase1(vha->vha_tgt.qla_tgt); + qlt_stop_phase2(vha->vha_tgt.qla_tgt); } return count; From 4c852f957a1e07229cc3e1ce7e8dd2b7c11eb782 Mon Sep 17 00:00:00 2001 From: Andreas Klinger Date: Mon, 4 May 2020 20:10:34 +0200 Subject: [PATCH 037/162] iio: bmp280: fix compensation of humidity [ Upstream commit dee2dabc0e4115b80945fe2c91603e634f4b4686 ] Limit the output of humidity compensation to the range between 0 and 100 percent. Depending on the calibration parameters of the individual sensor it happens, that a humidity above 100 percent or below 0 percent is calculated, which don't make sense in terms of relative humidity. Add a clamp to the compensation formula as described in the datasheet of the sensor in chapter 4.2.3. Although this clamp is documented, it was never in the driver of the kernel. It depends on the circumstances (calibration parameters, temperature, humidity) if one can see a value above 100 percent without the clamp. The writer of this patch was working with this type of sensor without noting this error. So it seems to be a rare event when this bug occures. Signed-off-by: Andreas Klinger Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/pressure/bmp280-core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 3204dff34e0a..ae415b4e381a 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -182,6 +182,8 @@ static u32 bmp280_compensate_humidity(struct bmp280_data *data, + (s32)2097152) * H2 + 8192) >> 14); var -= ((((var >> 15) * (var >> 15)) >> 7) * (s32)H1) >> 4; + var = clamp_val(var, 0, 419430400); + return var >> 12; }; From 6053683077c6d2a5218916acfa82794476cdcc58 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 11 May 2020 09:15:18 +0300 Subject: [PATCH 038/162] f2fs: report delalloc reserve as non-free in statfs for project quota [ Upstream commit baaa7ebf25c78c5cb712fac16b7f549100beddd3 ] This reserved space isn't committed yet but cannot be used for allocations. For userspace it has no difference from used space. See the same fix in ext4 commit f06925c73942 ("ext4: report delalloc reserve as non-free in statfs for project quota"). Fixes: ddc34e328d06 ("f2fs: introduce f2fs_statfs_project") Signed-off-by: Konstantin Khlebnikov Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 2d021a33914a..89319c352406 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -918,7 +918,8 @@ static int f2fs_statfs_project(struct super_block *sb, limit >>= sb->s_blocksize_bits; if (limit && buf->f_blocks > limit) { - curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits; + curblock = (dquot->dq_dqb.dqb_curspace + + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; buf->f_blocks = limit; buf->f_bfree = buf->f_bavail = (buf->f_blocks > curblock) ? From a5520d8f19a22f6f3a4d17a343045895d78c2bfd Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 6 May 2020 10:36:38 +0100 Subject: [PATCH 039/162] i2c: pxa: clear all master action bits in i2c_pxa_stop_message() [ Upstream commit e81c979f4e071d516aa27cf5a0c3939da00dc1ca ] If we timeout during a message transfer, the control register may contain bits that cause an action to be set. Read-modify-writing the register leaving these bits set may trigger the hardware to attempt one of these actions unintentionally. Always clear these bits when cleaning up after a message or after a timeout. Signed-off-by: Russell King Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-pxa.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index 600d264e080c..ecc84aea5131 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -709,11 +709,9 @@ static inline void i2c_pxa_stop_message(struct pxa_i2c *i2c) { u32 icr; - /* - * Clear the STOP and ACK flags - */ + /* Clear the START, STOP, ACK, TB and MA flags */ icr = readl(_ICR(i2c)); - icr &= ~(ICR_STOP | ICR_ACKNAK); + icr &= ~(ICR_START | ICR_STOP | ICR_ACKNAK | ICR_TB | ICR_MA); writel(icr, _ICR(i2c)); } From bce71fbd2e15fda3b381eba8490cf4989b3ed995 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 7 May 2020 10:58:06 +0200 Subject: [PATCH 040/162] usblp: poison URBs upon disconnect [ Upstream commit 296a193b06120aa6ae7cf5c0d7b5e5b55968026e ] syzkaller reported an URB that should have been killed to be active. We do not understand it, but this should fix the issue if it is real. Signed-off-by: Oliver Neukum Reported-by: syzbot+be5b5f86a162a6c281e6@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20200507085806.5793-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/class/usblp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 5e456a83779d..b0471ce34011 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -481,7 +481,8 @@ static int usblp_release(struct inode *inode, struct file *file) usb_autopm_put_interface(usblp->intf); if (!usblp->present) /* finish cleanup from disconnect */ - usblp_cleanup(usblp); + usblp_cleanup(usblp); /* any URBs must be dead */ + mutex_unlock(&usblp_mutex); return 0; } @@ -1388,9 +1389,11 @@ static void usblp_disconnect(struct usb_interface *intf) usblp_unlink_urbs(usblp); mutex_unlock(&usblp->mut); + usb_poison_anchored_urbs(&usblp->urbs); if (!usblp->used) usblp_cleanup(usblp); + mutex_unlock(&usblp_mutex); } From d7cb48e9dcfb494e0376af751c2c7d0d1f41d9b9 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Mon, 20 Apr 2020 22:29:09 +0200 Subject: [PATCH 041/162] dm mpath: switch paths in dm_blk_ioctl() code path [ Upstream commit 2361ae595352dec015d14292f1b539242d8446d6 ] SCSI LUN passthrough code such as qemu's "scsi-block" device model pass every IO to the host via SG_IO ioctls. Currently, dm-multipath calls choose_pgpath() only in the block IO code path, not in the ioctl code path (unless current_pgpath is NULL). This has the effect that no path switching and thus no load balancing is done for SCSI-passthrough IO, unless the active path fails. Fix this by using the same logic in multipath_prepare_ioctl() as in multipath_clone_and_map(). Note: The allegedly best path selection algorithm, service-time, still wouldn't work perfectly, because the io size of the current request is always set to 0. Changing that for the IO passthrough case would require the ioctl cmd and arg to be passed to dm's prepare_ioctl() method. Signed-off-by: Martin Wilck Reviewed-by: Hannes Reinecke Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-mpath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 8b7328666eaa..7c60aace8d25 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1815,7 +1815,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti, int r; current_pgpath = READ_ONCE(m->current_pgpath); - if (!current_pgpath) + if (!current_pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags)) current_pgpath = choose_pgpath(m, 0); if (current_pgpath) { From 7a177d5c553d3d1128d2e97ad9048ee5e04be3bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 30 Apr 2020 10:06:15 +0200 Subject: [PATCH 042/162] PCI: aardvark: Don't blindly enable ASPM L0s and don't write to read-only register MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 90c6cb4a355e7befcb557d217d1d8b8bd5875a05 ] Trying to change Link Status register does not have any effect as this is a read-only register. Trying to overwrite bits for Negotiated Link Width does not make sense. In future proper change of link width can be done via Lane Count Select bits in PCIe Control 0 register. Trying to unconditionally enable ASPM L0s via ASPM Control bits in Link Control register is wrong. There should be at least some detection if endpoint supports L0s as isn't mandatory. Moreover ASPM Control bits in Link Control register are controlled by pcie/aspm.c code which sets it according to system ASPM settings, immediately after aardvark driver probes. So setting these bits by aardvark driver has no long running effect. Remove code which touches ASPM L0s bits from this driver and let kernel's ASPM implementation to set ASPM state properly. Some users are reporting issues that this code is problematic for some Intel wifi cards and removing it fixes them, see e.g.: https://bugzilla.kernel.org/show_bug.cgi?id=196339 If problems with Intel wifi cards occur even after this commit, then pcie/aspm.c code could be modified / hooked to not enable ASPM L0s state for affected problematic cards. Link: https://lore.kernel.org/r/20200430080625.26070-3-pali@kernel.org Tested-by: Tomasz Maciej Nowak Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Acked-by: Rob Herring Acked-by: Thomas Petazzoni Signed-off-by: Sasha Levin --- drivers/pci/host/pci-aardvark.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 5f3048e75bec..c1db09fbbe04 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -365,10 +365,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) advk_pcie_wait_for_link(pcie); - reg = PCIE_CORE_LINK_L0S_ENTRY | - (1 << PCIE_CORE_LINK_WIDTH_SHIFT); - advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); - reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); reg |= PCIE_CORE_CMD_MEM_ACCESS_EN | PCIE_CORE_CMD_IO_ACCESS_EN | From 8bd3c08ab34cd74e58b2c8ff5e9519b8aab82932 Mon Sep 17 00:00:00 2001 From: Emmanuel Nicolet Date: Sat, 9 May 2020 18:58:32 +0000 Subject: [PATCH 043/162] ps3disk: use the default segment boundary [ Upstream commit 720bc316690bd27dea9d71510b50f0cd698ffc32 ] Since commit dcebd755926b ("block: use bio_for_each_bvec() to compute multi-page bvec count"), the kernel will bug_on on the PS3 because bio_split() is called with sectors == 0: kernel BUG at block/bio.c:1853! Oops: Exception in kernel mode, sig: 5 [#1] BE PAGE_SIZE=4K MMU=Hash PREEMPT SMP NR_CPUS=8 NUMA PS3 Modules linked in: firewire_sbp2 rtc_ps3(+) soundcore ps3_gelic(+) \ ps3rom(+) firewire_core ps3vram(+) usb_common crc_itu_t CPU: 0 PID: 97 Comm: blkid Not tainted 5.3.0-rc4 #1 NIP: c00000000027d0d0 LR: c00000000027d0b0 CTR: 0000000000000000 REGS: c00000000135ae90 TRAP: 0700 Not tainted (5.3.0-rc4) MSR: 8000000000028032 CR: 44008240 XER: 20000000 IRQMASK: 0 GPR00: c000000000289368 c00000000135b120 c00000000084a500 c000000004ff8300 GPR04: 0000000000000c00 c000000004c905e0 c000000004c905e0 000000000000ffff GPR08: 0000000000000000 0000000000000001 0000000000000000 000000000000ffff GPR12: 0000000000000000 c0000000008ef000 000000000000003e 0000000000080001 GPR16: 0000000000000100 000000000000ffff 0000000000000000 0000000000000004 GPR20: c00000000062fd7e 0000000000000001 000000000000ffff 0000000000000080 GPR24: c000000000781788 c00000000135b350 0000000000000080 c000000004c905e0 GPR28: c00000000135b348 c000000004ff8300 0000000000000000 c000000004c90000 NIP [c00000000027d0d0] .bio_split+0x28/0xac LR [c00000000027d0b0] .bio_split+0x8/0xac Call Trace: [c00000000135b120] [c00000000027d130] .bio_split+0x88/0xac (unreliable) [c00000000135b1b0] [c000000000289368] .__blk_queue_split+0x11c/0x53c [c00000000135b2d0] [c00000000028f614] .blk_mq_make_request+0x80/0x7d4 [c00000000135b3d0] [c000000000283a8c] .generic_make_request+0x118/0x294 [c00000000135b4b0] [c000000000283d34] .submit_bio+0x12c/0x174 [c00000000135b580] [c000000000205a44] .mpage_bio_submit+0x3c/0x4c [c00000000135b600] [c000000000206184] .mpage_readpages+0xa4/0x184 [c00000000135b750] [c0000000001ff8fc] .blkdev_readpages+0x24/0x38 [c00000000135b7c0] [c0000000001589f0] .read_pages+0x6c/0x1a8 [c00000000135b8b0] [c000000000158c74] .__do_page_cache_readahead+0x118/0x184 [c00000000135b9b0] [c0000000001591a8] .force_page_cache_readahead+0xe4/0xe8 [c00000000135ba50] [c00000000014fc24] .generic_file_read_iter+0x1d8/0x830 [c00000000135bb50] [c0000000001ffadc] .blkdev_read_iter+0x40/0x5c [c00000000135bbc0] [c0000000001b9e00] .new_sync_read+0x144/0x1a0 [c00000000135bcd0] [c0000000001bc454] .vfs_read+0xa0/0x124 [c00000000135bd70] [c0000000001bc7a4] .ksys_read+0x70/0xd8 [c00000000135be20] [c00000000000a524] system_call+0x5c/0x70 Instruction dump: 7fe3fb78 482e30dc 7c0802a6 482e3085 7c9e2378 f821ff71 7ca42b78 7d3e00d0 7c7d1b78 79290fe0 7cc53378 69290001 <0b090000> 81230028 7bca0020 7929ba62 [ end trace 313fec760f30aa1f ]--- The problem originates from setting the segment boundary of the request queue to -1UL. This makes get_max_segment_size() return zero when offset is zero, whatever the max segment size. The test with BLK_SEG_BOUNDARY_MASK fails and 'mask - (mask & offset) + 1' overflows to zero in the return statement. Not setting the segment boundary and using the default value (BLK_SEG_BOUNDARY_MASK) fixes the problem. Signed-off-by: Emmanuel Nicolet Signed-off-by: Geoff Levand Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/060a416c43138f45105c0540eff1a45539f7e2fc.1589049250.git.geoff@infradead.org Signed-off-by: Sasha Levin --- drivers/block/ps3disk.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 075662f2cf46..d20f66d57804 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -468,7 +468,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) blk_queue_bounce_limit(queue, BLK_BOUNCE_HIGH); blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9); - blk_queue_segment_boundary(queue, -1UL); blk_queue_dma_alignment(queue, dev->blk_size-1); blk_queue_logical_block_size(queue, dev->blk_size); From f87ebe6764ecd7235d08cfb084db021c81941b88 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sun, 10 May 2020 12:16:56 -0400 Subject: [PATCH 044/162] vfio/pci: fix memory leaks in alloc_perm_bits() [ Upstream commit 3e63b94b6274324ff2e7d8615df31586de827c4e ] vfio_pci_disable() calls vfio_config_free() but forgets to call free_perm_bits() resulting in memory leaks, unreferenced object 0xc000000c4db2dee0 (size 16): comm "qemu-kvm", pid 4305, jiffies 4295020272 (age 3463.780s) hex dump (first 16 bytes): 00 00 ff 00 ff ff ff ff ff ff ff ff ff ff 00 00 ................ backtrace: [<00000000a6a4552d>] alloc_perm_bits+0x58/0xe0 [vfio_pci] [<00000000ac990549>] vfio_config_init+0xdf0/0x11b0 [vfio_pci] init_pci_cap_msi_perm at drivers/vfio/pci/vfio_pci_config.c:1125 (inlined by) vfio_msi_cap_len at drivers/vfio/pci/vfio_pci_config.c:1180 (inlined by) vfio_cap_len at drivers/vfio/pci/vfio_pci_config.c:1241 (inlined by) vfio_cap_init at drivers/vfio/pci/vfio_pci_config.c:1468 (inlined by) vfio_config_init at drivers/vfio/pci/vfio_pci_config.c:1707 [<000000006db873a1>] vfio_pci_open+0x234/0x700 [vfio_pci] [<00000000630e1906>] vfio_group_fops_unl_ioctl+0x8e0/0xb84 [vfio] [<000000009e34c54f>] ksys_ioctl+0xd8/0x130 [<000000006577923d>] sys_ioctl+0x28/0x40 [<000000006d7b1cf2>] system_call_exception+0x114/0x1e0 [<0000000008ea7dd5>] system_call_common+0xf0/0x278 unreferenced object 0xc000000c4db2e330 (size 16): comm "qemu-kvm", pid 4305, jiffies 4295020272 (age 3463.780s) hex dump (first 16 bytes): 00 ff ff 00 ff ff ff ff ff ff ff ff ff ff 00 00 ................ backtrace: [<000000004c71914f>] alloc_perm_bits+0x44/0xe0 [vfio_pci] [<00000000ac990549>] vfio_config_init+0xdf0/0x11b0 [vfio_pci] [<000000006db873a1>] vfio_pci_open+0x234/0x700 [vfio_pci] [<00000000630e1906>] vfio_group_fops_unl_ioctl+0x8e0/0xb84 [vfio] [<000000009e34c54f>] ksys_ioctl+0xd8/0x130 [<000000006577923d>] sys_ioctl+0x28/0x40 [<000000006d7b1cf2>] system_call_exception+0x114/0x1e0 [<0000000008ea7dd5>] system_call_common+0xf0/0x278 Fixes: 89e1f7d4c66d ("vfio: Add PCI device driver") Signed-off-by: Qian Cai [aw: rolled in follow-up patch] Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- drivers/vfio/pci/vfio_pci_config.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 423ea1f98441..c2d300bc37f6 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1732,8 +1732,11 @@ void vfio_config_free(struct vfio_pci_device *vdev) vdev->vconfig = NULL; kfree(vdev->pci_config_map); vdev->pci_config_map = NULL; - kfree(vdev->msi_perm); - vdev->msi_perm = NULL; + if (vdev->msi_perm) { + free_perm_bits(vdev->msi_perm); + kfree(vdev->msi_perm); + vdev->msi_perm = NULL; + } } /* From 66f3c8e5d3a419767f30fb79ecc050aeed0c7353 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 18 Apr 2020 09:07:51 +0200 Subject: [PATCH 045/162] m68k/PCI: Fix a memory leak in an error handling path [ Upstream commit c3f4ec050f56eeab7c1f290321f9b762c95bd332 ] If 'ioremap' fails, we must free 'bridge', as done in other error handling path bellow. Fixes: 19cc4c843f40 ("m68k/PCI: Replace pci_fixup_irqs() call with host bridge IRQ mapping hooks") Signed-off-by: Christophe JAILLET Reviewed-by: Geert Uytterhoeven Signed-off-by: Greg Ungerer Signed-off-by: Sasha Levin --- arch/m68k/coldfire/pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c index 3097fa2ca746..1e428d18d268 100644 --- a/arch/m68k/coldfire/pci.c +++ b/arch/m68k/coldfire/pci.c @@ -316,8 +316,10 @@ static int __init mcf_pci_init(void) /* Keep a virtual mapping to IO/config space active */ iospace = (unsigned long) ioremap(PCI_IO_PA, PCI_IO_SIZE); - if (iospace == 0) + if (iospace == 0) { + pci_free_host_bridge(bridge); return -ENODEV; + } pr_info("Coldfire: PCI IO/config window mapped to 0x%x\n", (u32) iospace); From 696ad8b6100063d5daa70550408f00f6c8b667b1 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 27 Apr 2020 09:48:29 +0200 Subject: [PATCH 046/162] mfd: wm8994: Fix driver operation if loaded as modules [ Upstream commit d4f9b5428b53dd67f49ee8deed8d4366ed6b1933 ] WM8994 chip has built-in regulators, which might be used for chip operation. They are controlled by a separate wm8994-regulator driver, which should be loaded before this driver calls regulator_get(), because that driver also provides consumer-supply mapping for the them. If that driver is not yet loaded, regulator core substitute them with dummy regulator, what breaks chip operation, because the built-in regulators are never enabled. Fix this by annotating this driver with MODULE_SOFTDEP() "pre" dependency to "wm8994_regulator" module. Signed-off-by: Marek Szyprowski Acked-by: Charles Keepax Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/wm8994-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c index 953d0790ffd5..3259fb82d3c4 100644 --- a/drivers/mfd/wm8994-core.c +++ b/drivers/mfd/wm8994-core.c @@ -696,3 +696,4 @@ module_i2c_driver(wm8994_i2c_driver); MODULE_DESCRIPTION("Core support for the WM8994 audio CODEC"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mark Brown "); +MODULE_SOFTDEP("pre: wm8994_regulator"); From aa21b9645d997088dfc8c365cc9643f39f178a29 Mon Sep 17 00:00:00 2001 From: Xiyu Yang Date: Mon, 25 May 2020 22:16:24 +0800 Subject: [PATCH 047/162] scsi: lpfc: Fix lpfc_nodelist leak when processing unsolicited event [ Upstream commit 7217e6e694da3aae6d17db8a7f7460c8d4817ebf ] In order to create or activate a new node, lpfc_els_unsol_buffer() invokes lpfc_nlp_init() or lpfc_enable_node() or lpfc_nlp_get(), all of them will return a reference of the specified lpfc_nodelist object to "ndlp" with increased refcnt. When lpfc_els_unsol_buffer() returns, local variable "ndlp" becomes invalid, so the refcount should be decreased to keep refcount balanced. The reference counting issue happens in one exception handling path of lpfc_els_unsol_buffer(). When "ndlp" in DEV_LOSS, the function forgets to decrease the refcnt increased by lpfc_nlp_init() or lpfc_enable_node() or lpfc_nlp_get(), causing a refcnt leak. Fix this issue by calling lpfc_nlp_put() when "ndlp" in DEV_LOSS. Link: https://lore.kernel.org/r/1590416184-52592-1-git-send-email-xiyuyang19@fudan.edu.cn Reviewed-by: Daniel Wagner Reviewed-by: James Smart Signed-off-by: Xiyu Yang Signed-off-by: Xin Tan Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_els.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 4c84c2ae1112..db1111f7e85a 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -7913,6 +7913,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, spin_lock_irq(shost->host_lock); if (ndlp->nlp_flag & NLP_IN_DEV_LOSS) { spin_unlock_irq(shost->host_lock); + if (newnode) + lpfc_nlp_put(ndlp); goto dropit; } spin_unlock_irq(shost->host_lock); From 2f2ef08efa4696c598e127f1a35bb758576f9dbc Mon Sep 17 00:00:00 2001 From: Alain Volmat Date: Sun, 22 Mar 2020 15:07:40 +0100 Subject: [PATCH 048/162] clk: clk-flexgen: fix clock-critical handling [ Upstream commit a403bbab1a73d798728d76931cab3ff0399b9560 ] Fixes an issue leading to having all clocks following a critical clocks marked as well as criticals. Fixes: fa6415affe20 ("clk: st: clk-flexgen: Detect critical clocks") Signed-off-by: Alain Volmat Link: https://lkml.kernel.org/r/20200322140740.3970-1-avolmat@me.com Reviewed-by: Patrice Chotard Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/st/clk-flexgen.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c index 918ba3164da9..cd856210db58 100644 --- a/drivers/clk/st/clk-flexgen.c +++ b/drivers/clk/st/clk-flexgen.c @@ -373,6 +373,7 @@ static void __init st_of_flexgen_setup(struct device_node *np) break; } + flex_flags &= ~CLK_IS_CRITICAL; of_clk_detect_critical(np, i, &flex_flags); /* From 2412141022b117fb21343492e6cad5b6c733782a Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Mon, 25 May 2020 16:13:03 +0530 Subject: [PATCH 049/162] powerpc/perf/hv-24x7: Fix inconsistent output values incase multiple hv-24x7 events run [ Upstream commit b4ac18eead28611ff470d0f47a35c4e0ac080d9c ] Commit 2b206ee6b0df ("powerpc/perf/hv-24x7: Display change in counter values")' added to print _change_ in the counter value rather then raw value for 24x7 counters. Incase of transactions, the event count is set to 0 at the beginning of the transaction. It also sets the event's prev_count to the raw value at the time of initialization. Because of setting event count to 0, we are seeing some weird behaviour, whenever we run multiple 24x7 events at a time. For example: command#: ./perf stat -e "{hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/, hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/}" -C 0 -I 1000 sleep 100 1.000121704 120 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 1.000121704 5 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 2.000357733 8 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 2.000357733 10 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 3.000495215 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 3.000495215 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 4.000641884 56 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 4.000641884 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 5.000791887 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ Getting these large values in case we do -I. As we are setting event_count to 0, for interval case, overall event_count is not coming in incremental order. As we may can get new delta lesser then previous count. Because of which when we print intervals, we are getting negative value which create these large values. This patch removes part where we set event_count to 0 in function 'h_24x7_event_read'. There won't be much impact as we do set event->hw.prev_count to the raw value at the time of initialization to print change value. With this patch In power9 platform command#: ./perf stat -e "{hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/, hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/}" -C 0 -I 1000 sleep 100 1.000117685 93 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 1.000117685 1 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 2.000349331 98 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 2.000349331 2 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 3.000495900 131 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 3.000495900 4 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 4.000645920 204 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ 4.000645920 61 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/ 4.284169997 22 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/ Suggested-by: Sukadev Bhattiprolu Signed-off-by: Kajol Jain Tested-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200525104308.9814-2-kjain@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/perf/hv-24x7.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 72238eedc360..2bb798918483 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1413,16 +1413,6 @@ static void h_24x7_event_read(struct perf_event *event) h24x7hw = &get_cpu_var(hv_24x7_hw); h24x7hw->events[i] = event; put_cpu_var(h24x7hw); - /* - * Clear the event count so we can compute the _change_ - * in the 24x7 raw counter value at the end of the txn. - * - * Note that we could alternatively read the 24x7 value - * now and save its value in event->hw.prev_count. But - * that would require issuing a hcall, which would then - * defeat the purpose of using the txn interface. - */ - local64_set(&event->count, 0); } put_cpu_var(hv_24x7_reqb); From 0c4fb76c4e711d9e4e70ddc6732310a17076175d Mon Sep 17 00:00:00 2001 From: Xiyu Yang Date: Mon, 25 May 2020 22:15:41 +0800 Subject: [PATCH 050/162] nfsd: Fix svc_xprt refcnt leak when setup callback client failed [ Upstream commit a4abc6b12eb1f7a533c2e7484cfa555454ff0977 ] nfsd4_process_cb_update() invokes svc_xprt_get(), which increases the refcount of the "c->cn_xprt". The reference counting issue happens in one exception handling path of nfsd4_process_cb_update(). When setup callback client failed, the function forgets to decrease the refcnt increased by svc_xprt_get(), causing a refcnt leak. Fix this issue by calling svc_xprt_put() when setup callback client failed. Signed-off-by: Xiyu Yang Signed-off-by: Xin Tan Signed-off-by: J. Bruce Fields Signed-off-by: Sasha Levin --- fs/nfsd/nfs4callback.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 80aeb19b176b..22b784e7ef50 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1161,6 +1161,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) err = setup_callback_client(clp, &conn, ses); if (err) { nfsd4_mark_cb_down(clp, err); + if (c) + svc_xprt_put(c->cn_xprt); return; } } From 6706e3e7f81891c50e19b1d7a3b9cf349c0e7b10 Mon Sep 17 00:00:00 2001 From: Pingfan Liu Date: Wed, 1 Apr 2020 22:00:44 +0800 Subject: [PATCH 051/162] powerpc/crashkernel: Take "mem=" option into account [ Upstream commit be5470e0c285a68dc3afdea965032f5ddc8269d7 ] 'mem=" option is an easy way to put high pressure on memory during some test. Hence after applying the memory limit, instead of total mem, the actual usable memory should be considered when reserving mem for crashkernel. Otherwise the boot up may experience OOM issue. E.g. it would reserve 4G prior to the change and 512M afterward, if passing crashkernel="2G-4G:384M,4G-16G:512M,16G-64G:1G,64G-128G:2G,128G-:4G", and mem=5G on a 256G machine. This issue is powerpc specific because it puts higher priority on fadump and kdump reservation than on "mem=". Referring the following code: if (fadump_reserve_mem() == 0) reserve_crashkernel(); ... /* Ensure that total memory size is page-aligned. */ limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); memblock_enforce_memory_limit(limit); While on other arches, the effect of "mem=" takes a higher priority and pass through memblock_phys_mem_size() before calling reserve_crashkernel(). Signed-off-by: Pingfan Liu Reviewed-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1585749644-4148-1-git-send-email-kernelfans@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/machine_kexec.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 9dafd7af39b8..cb4d6cd949fc 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -113,11 +113,12 @@ void machine_kexec(struct kimage *image) void __init reserve_crashkernel(void) { - unsigned long long crash_size, crash_base; + unsigned long long crash_size, crash_base, total_mem_sz; int ret; + total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size(); /* use common parsing */ - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; @@ -176,6 +177,7 @@ void __init reserve_crashkernel(void) /* Crash kernel trumps memory limit */ if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; + total_mem_sz = memory_limit; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", memory_limit); } @@ -184,7 +186,7 @@ void __init reserve_crashkernel(void) "for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crashk_res.start >> 20), - (unsigned long)(memblock_phys_mem_size() >> 20)); + (unsigned long)(total_mem_sz >> 20)); if (!memblock_is_region_memory(crashk_res.start, crash_size) || memblock_reserve(crashk_res.start, crash_size)) { From 11e1f4a58647c6f3292b8f71baeaf6ee1a64a741 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Thu, 4 Jun 2020 20:18:51 +0800 Subject: [PATCH 052/162] yam: fix possible memory leak in yam_init_driver [ Upstream commit 98749b7188affbf2900c2aab704a8853901d1139 ] If register_netdev(dev) fails, free_netdev(dev) needs to be called, otherwise a memory leak will occur. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Hulk Robot Signed-off-by: Wang Hai Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/hamradio/yam.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 16a6e1193912..b74c735a423d 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -1162,6 +1162,7 @@ static int __init yam_init_driver(void) err = register_netdev(dev); if (err) { printk(KERN_WARNING "yam: cannot register net device %s\n", dev->name); + free_netdev(dev); goto error; } yam_devs[i] = dev; From cb15a85dd4fb0b63c8d9af1b1a891699f7da65de Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 9 Jan 2019 12:22:28 -0700 Subject: [PATCH 053/162] NTB: Fix the default port and peer numbers for legacy drivers [ Upstream commit fc8b086d9dbd57458d136c4fa70ee26f832c3a2e ] When the commit adding ntb_default_port_number() and ntb_default_peer_port_number() entered the kernel there was no users of it so it was impossible to tell what the API needed. When a user finally landed a year later (ntb_pingpong) there were more NTB topologies were created and no consideration was considered to how other drivers had changed. Now that there is a user it can be fixed to provide a sensible default for the legacy drivers that do not implement ntb_{peer_}port_number(). Seeing ntb_pingpong doesn't check error codes returning EINVAL was also not sensible. Patches for ntb_pingpong and ntb_perf follow (which are broken otherwise) to support hardware that doesn't have port numbers. This is important not only to not break support with existing drivers but for the cross link topology which, due to its perfect symmetry, cannot assign unique port numbers to each side. Fixes: 1e5301196a88 ("NTB: Add indexed ports NTB API") Signed-off-by: Logan Gunthorpe Acked-by: Allen Hubbe Tested-by: Alexander Fomichev Signed-off-by: Jon Mason Signed-off-by: Sasha Levin --- drivers/ntb/ntb.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c index 03b80d89b980..b75ec229b39a 100644 --- a/drivers/ntb/ntb.c +++ b/drivers/ntb/ntb.c @@ -216,10 +216,8 @@ int ntb_default_port_number(struct ntb_dev *ntb) case NTB_TOPO_B2B_DSD: return NTB_PORT_SEC_DSD; default: - break; + return 0; } - - return -EINVAL; } EXPORT_SYMBOL(ntb_default_port_number); @@ -242,10 +240,8 @@ int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx) case NTB_TOPO_B2B_DSD: return NTB_PORT_PRI_USD; default: - break; + return 0; } - - return -EINVAL; } EXPORT_SYMBOL(ntb_default_peer_port_number); From 466cd9ebc50402f9e3d8b8534d7e1585640decff Mon Sep 17 00:00:00 2001 From: ashimida Date: Tue, 2 Jun 2020 15:45:17 +0800 Subject: [PATCH 054/162] mksysmap: Fix the mismatch of '.L' symbols in System.map [ Upstream commit 72d24accf02add25e08733f0ecc93cf10fcbd88c ] When System.map was generated, the kernel used mksysmap to filter the kernel symbols, but all the symbols with the second letter 'L' in the kernel were filtered out, not just the symbols starting with 'dot + L'. For example: ashimida@ubuntu:~/linux$ cat System.map |grep ' .L' ashimida@ubuntu:~/linux$ nm -n vmlinux |grep ' .L' ffff0000088028e0 t bLength_show ...... ffff0000092e0408 b PLLP_OUTC_lock ffff0000092e0410 b PLLP_OUTA_lock The original intent should be to filter out all local symbols starting with '.L', so the dot should be escaped. Fixes: 00902e984732 ("mksysmap: Add h8300 local symbol pattern") Signed-off-by: ashimida Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/mksysmap | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mksysmap b/scripts/mksysmap index a35acc0d0b82..9aa23d15862a 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -41,4 +41,4 @@ # so we just ignore them to let readprofile continue to work. # (At least sparc64 has __crc_ in the middle). -$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( .L\)' > $2 +$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( \.L\)' > $2 From 8906aa8e570562f289b8e42657121225f15f7453 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Fri, 5 Jun 2020 18:12:21 -0700 Subject: [PATCH 055/162] apparmor: fix introspection of of task mode for unconfined tasks [ Upstream commit dd2569fbb053719f7df7ef8fdbb45cf47156a701 ] Fix two issues with introspecting the task mode. 1. If a task is attached to a unconfined profile that is not the ns->unconfined profile then. Mode the mode is always reported as - $ ps -Z LABEL PID TTY TIME CMD unconfined 1287 pts/0 00:00:01 bash test (-) 1892 pts/0 00:00:00 ps instead of the correct value of (unconfined) as shown below $ ps -Z LABEL PID TTY TIME CMD unconfined 2483 pts/0 00:00:01 bash test (unconfined) 3591 pts/0 00:00:00 ps 2. if a task is confined by a stack of profiles that are unconfined the output of label mode is again the incorrect value of (-) like above, instead of (unconfined). This is because the visibile profile count increment is skipped by the special casing of unconfined. Fixes: f1bd904175e8 ("apparmor: add the base fns() for domain labels") Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/label.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/security/apparmor/label.c b/security/apparmor/label.c index ea63710442ae..212a0f39ddae 100644 --- a/security/apparmor/label.c +++ b/security/apparmor/label.c @@ -1536,13 +1536,13 @@ static const char *label_modename(struct aa_ns *ns, struct aa_label *label, label_for_each(i, label, profile) { if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) { - if (profile->mode == APPARMOR_UNCONFINED) + count++; + if (profile == profile->ns->unconfined) /* special case unconfined so stacks with * unconfined don't report as mixed. ie. * profile_foo//&:ns1:unconfined (mixed) */ continue; - count++; if (mode == -1) mode = profile->mode; else if (mode != profile->mode) From b69f3d2711c776ff82aa0b62613f7d0f2100512b Mon Sep 17 00:00:00 2001 From: Simon Arlott Date: Sat, 30 May 2020 18:59:44 +0100 Subject: [PATCH 056/162] scsi: sr: Fix sr_probe() missing deallocate of device minor [ Upstream commit 6555781b3fdec5e94e6914511496144241df7dee ] If the cdrom fails to be registered then the device minor should be deallocated. Link: https://lore.kernel.org/r/072dac4b-8402-4de8-36bd-47e7588969cd@0882a8b5-c6c3-11e9-b005-00805fc181fe Signed-off-by: Simon Arlott Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/sr.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index d0389b20574d..5be3d6b7991b 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -748,7 +748,7 @@ static int sr_probe(struct device *dev) cd->cdi.disk = disk; if (register_cdrom(&cd->cdi)) - goto fail_put; + goto fail_minor; /* * Initialize block layer runtime PM stuffs before the @@ -766,6 +766,10 @@ static int sr_probe(struct device *dev) return 0; +fail_minor: + spin_lock(&sr_index_lock); + clear_bit(minor, sr_index_bits); + spin_unlock(&sr_index_lock); fail_put: put_disk(disk); fail_free: From 06c99f4951c6f26764ff393552809314c3d48ef3 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 3 Jun 2020 15:36:32 -0500 Subject: [PATCH 057/162] scsi: ibmvscsi: Don't send host info in adapter info MAD after LPM [ Upstream commit 4919b33b63c8b69d8dcf2b867431d0e3b6dc6d28 ] The adapter info MAD is used to send the client info and receive the host info as a response. A persistent buffer is used and as such the client info is overwritten after the response. During the course of a normal adapter reset the client info is refreshed in the buffer in preparation for sending the adapter info MAD. However, in the special case of LPM where we reenable the CRQ instead of a full CRQ teardown and reset we fail to refresh the client info in the adapter info buffer. As a result, after Live Partition Migration (LPM) we erroneously report the host's info as our own. [mkp: typos] Link: https://lore.kernel.org/r/20200603203632.18426-1-tyreld@linux.ibm.com Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ibmvscsi/ibmvscsi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 83645a1c6f82..aff868afe68d 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -429,6 +429,8 @@ static int ibmvscsi_reenable_crq_queue(struct crq_queue *queue, int rc = 0; struct vio_dev *vdev = to_vio_dev(hostdata->dev); + set_adapter_info(hostdata); + /* Re-enable the CRQ */ do { if (rc) From ac0a8b95d3e1999c4f6b59d7ab867d0d891bafac Mon Sep 17 00:00:00 2001 From: Chen Zhou Date: Wed, 1 Apr 2020 11:00:17 +0800 Subject: [PATCH 058/162] staging: greybus: fix a missing-check bug in gb_lights_light_config() [ Upstream commit 9bb086e5ba9495ac150fbbcc5c8c2bccc06261dd ] In gb_lights_light_config(), 'light->name' is allocated by kstrndup(). It returns NULL when fails, add check for it. Signed-off-by: Chen Zhou Acked-by: Rui Miguel Silva Link: https://lore.kernel.org/r/20200401030017.100274-1-chenzhou10@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/greybus/light.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/staging/greybus/light.c b/drivers/staging/greybus/light.c index 4e7575147775..9fab0e2751aa 100644 --- a/drivers/staging/greybus/light.c +++ b/drivers/staging/greybus/light.c @@ -1033,7 +1033,8 @@ static int gb_lights_light_config(struct gb_lights *glights, u8 id) light->channels_count = conf.channel_count; light->name = kstrndup(conf.name, NAMES_MAX, GFP_KERNEL); - + if (!light->name) + return -ENOMEM; light->channels = kcalloc(light->channels_count, sizeof(struct gb_channel), GFP_KERNEL); if (!light->channels) From ca70ee74bcfb08d90585a1d2ef23153131f8cf0f Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Tue, 7 Apr 2020 23:43:30 -0700 Subject: [PATCH 059/162] scsi: qedi: Do not flush offload work if ARP not resolved [ Upstream commit 927527aea0e2a9c1d336c7d33f77f1911481d008 ] For an unreachable target, offload_work is not initialized and the endpoint state is set to OFLDCONN_NONE. This results in a WARN_ON due to the check of the work function field being set to zero. ------------[ cut here ]------------ WARNING: CPU: 24 PID: 18587 at ../kernel/workqueue.c:3037 __flush_work+0x1c1/0x1d0 : Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 02/01/2020 RIP: 0010:__flush_work+0x1c1/0x1d0 Code: ba 6d 00 03 80 c9 f0 eb b6 48 c7 c7 20 ee 6c a4 e8 52 d3 04 00 0f 0b 31 c0 e9 d1 fe ff ff 48 c7 c7 20 ee 6c a4 e8 3d d3 04 00 <0f> 0b 31 c0 e9 bc fe ff ff e8 11 f3 f 00 31 f6 RSP: 0018:ffffac5a8cd47a80 EFLAGS: 00010282 RAX: 0000000000000024 RBX: ffff98d68c1fcaf0 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff98ce9fd99898 RDI: ffff98ce9fd99898 RBP: ffff98d68c1fcbc0 R08: 00000000000006fa R09: 0000000000000001 R10: ffffac5a8cd47b50 R11: 0000000000000001 R12: 0000000000000000 R13: 000000000000489b R14: ffff98d68c1fc800 R15: ffff98d692132c00 FS: 00007f65f7f62280(0000) GS:ffff98ce9fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffd2435e880 CR3: 0000000809334003 CR4: 00000000007606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ? class_create_release+0x40/0x40 ? klist_put+0x2c/0x80 qedi_ep_disconnect+0xdd/0x400 [qedi] iscsi_if_ep_disconnect.isra.20+0x59/0x70 [scsi_transport_iscsi] iscsi_if_rx+0x129b/0x1670 [scsi_transport_iscsi] ? __netlink_lookup+0xe7/0x160 netlink_unicast+0x21d/0x300 netlink_sendmsg+0x30f/0x430 sock_sendmsg+0x5b/0x60 ____sys_sendmsg+0x1e2/0x240 ? copy_msghdr_from_user+0xd9/0x160 ___sys_sendmsg+0x88/0xd0 ? ___sys_recvmsg+0xa2/0xe0 ? hrtimer_try_to_cancel+0x25/0x100 ? do_nanosleep+0x9c/0x170 ? __sys_sendmsg+0x5e/0xa0 __sys_sendmsg+0x5e/0xa0 do_syscall_64+0x60/0x1f0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f65f6f16107 Code: 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 80 00 00 00 00 8b 05 aa d2 2b 00 48 63 d2 48 63 ff 85 c0 75 18 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 59 f3 c3 0f 1f 8 0 00 00 00 00 53 48 89 f3 48 RSP: 002b:00007ffd24367ca8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000055a7aeaaf110 RCX: 00007f65f6f16107 RDX: 0000000000000000 RSI: 00007ffd24367cc0 RDI: 0000000000000003 RBP: 0000000000000070 R08: 0000000000000000 R09: 0000000000000000 R10: 000000000000075c R11: 0000000000000246 R12: 00007ffd24367cc0 R13: 000055a7ae560008 R14: 00007ffd24367db0 R15: 0000000000000000 ---[ end trace 54f499c05d41f8bb ]--- Only flush if the connection endpoint state if different from OFLDCONN_NONE. [mkp: clarified commit desc] Link: https://lore.kernel.org/r/20200408064332.19377-5-mrangankar@marvell.com Reviewed-by: Lee Duncan Signed-off-by: Nilesh Javali Signed-off-by: Manish Rangankar Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedi/qedi_iscsi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 1effac1111d5..fb6439bc1d9a 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -1007,7 +1007,8 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) if (qedi_ep->state == EP_STATE_OFLDCONN_START) goto ep_exit_recover; - flush_work(&qedi_ep->offload_work); + if (qedi_ep->state != EP_STATE_OFLDCONN_NONE) + flush_work(&qedi_ep->offload_work); if (qedi_ep->conn) { qedi_conn = qedi_ep->conn; From 99703c921864a318e3e8aae74fde071b1ff35bea Mon Sep 17 00:00:00 2001 From: Alexander Tsoy Date: Fri, 24 Apr 2020 05:24:48 +0300 Subject: [PATCH 060/162] ALSA: usb-audio: Improve frames size computation [ Upstream commit f0bd62b64016508938df9babe47f65c2c727d25c ] For computation of the the next frame size current value of fs/fps and accumulated fractional parts of fs/fps are used, where values are stored in Q16.16 format. This is quite natural for computing frame size for asynchronous endpoints driven by explicit feedback, since in this case fs/fps is a value provided by the feedback endpoint and it's already in the Q format. If an error is accumulated over time, the device can adjust fs/fps value to prevent buffer overruns/underruns. But for synchronous endpoints the accuracy provided by these computations is not enough. Due to accumulated error the driver periodically produces frames with incorrect size (+/- 1 audio sample). This patch fixes this issue by implementing a different algorithm for frame size computation. It is based on accumulating of the remainders from division fs/fps and it doesn't accumulate errors over time. This new method is enabled for synchronous and adaptive playback endpoints. Signed-off-by: Alexander Tsoy Link: https://lore.kernel.org/r/20200424022449.14972-1-alexander@tsoy.me Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/card.h | 4 ++++ sound/usb/endpoint.c | 43 ++++++++++++++++++++++++++++++++++++++----- sound/usb/endpoint.h | 1 + sound/usb/pcm.c | 2 ++ 4 files changed, 45 insertions(+), 5 deletions(-) diff --git a/sound/usb/card.h b/sound/usb/card.h index ed87cc83eb47..9dbcbb27c28e 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -81,6 +81,10 @@ struct snd_usb_endpoint { dma_addr_t sync_dma; /* DMA address of syncbuf */ unsigned int pipe; /* the data i/o pipe */ + unsigned int framesize[2]; /* small/large frame sizes in samples */ + unsigned int sample_rem; /* remainder from division fs/fps */ + unsigned int sample_accum; /* sample accumulator */ + unsigned int fps; /* frames per second */ unsigned int freqn; /* nominal sampling rate in fs/fps in Q16.16 format */ unsigned int freqm; /* momentary sampling rate in fs/fps in Q16.16 format */ int freqshift; /* how much to shift the feedback value to get Q16.16 */ diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 8caf0b57f9c6..841219560872 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -137,12 +137,12 @@ int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep) /* * For streaming based on information derived from sync endpoints, - * prepare_outbound_urb_sizes() will call next_packet_size() to + * prepare_outbound_urb_sizes() will call slave_next_packet_size() to * determine the number of samples to be sent in the next packet. * - * For implicit feedback, next_packet_size() is unused. + * For implicit feedback, slave_next_packet_size() is unused. */ -int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep) +int snd_usb_endpoint_slave_next_packet_size(struct snd_usb_endpoint *ep) { unsigned long flags; int ret; @@ -159,6 +159,29 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep) return ret; } +/* + * For adaptive and synchronous endpoints, prepare_outbound_urb_sizes() + * will call next_packet_size() to determine the number of samples to be + * sent in the next packet. + */ +int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep) +{ + int ret; + + if (ep->fill_max) + return ep->maxframesize; + + ep->sample_accum += ep->sample_rem; + if (ep->sample_accum >= ep->fps) { + ep->sample_accum -= ep->fps; + ret = ep->framesize[1]; + } else { + ret = ep->framesize[0]; + } + + return ret; +} + static void retire_outbound_urb(struct snd_usb_endpoint *ep, struct snd_urb_ctx *urb_ctx) { @@ -203,6 +226,8 @@ static void prepare_silent_urb(struct snd_usb_endpoint *ep, if (ctx->packet_size[i]) counts = ctx->packet_size[i]; + else if (ep->sync_master) + counts = snd_usb_endpoint_slave_next_packet_size(ep); else counts = snd_usb_endpoint_next_packet_size(ep); @@ -889,10 +914,17 @@ int snd_usb_endpoint_set_params(struct snd_usb_endpoint *ep, ep->maxpacksize = fmt->maxpacksize; ep->fill_max = !!(fmt->attributes & UAC_EP_CS_ATTR_FILL_MAX); - if (snd_usb_get_speed(ep->chip->dev) == USB_SPEED_FULL) + if (snd_usb_get_speed(ep->chip->dev) == USB_SPEED_FULL) { ep->freqn = get_usb_full_speed_rate(rate); - else + ep->fps = 1000; + } else { ep->freqn = get_usb_high_speed_rate(rate); + ep->fps = 8000; + } + + ep->sample_rem = rate % ep->fps; + ep->framesize[0] = rate / ep->fps; + ep->framesize[1] = (rate + (ep->fps - 1)) / ep->fps; /* calculate the frequency in 16.16 format */ ep->freqm = ep->freqn; @@ -951,6 +983,7 @@ int snd_usb_endpoint_start(struct snd_usb_endpoint *ep) ep->active_mask = 0; ep->unlink_mask = 0; ep->phase = 0; + ep->sample_accum = 0; snd_usb_endpoint_start_quirk(ep); diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h index 63a39d4fa8d8..d23fa0a8c11b 100644 --- a/sound/usb/endpoint.h +++ b/sound/usb/endpoint.h @@ -28,6 +28,7 @@ void snd_usb_endpoint_release(struct snd_usb_endpoint *ep); void snd_usb_endpoint_free(struct snd_usb_endpoint *ep); int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep); +int snd_usb_endpoint_slave_next_packet_size(struct snd_usb_endpoint *ep); int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep); void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep, diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index ff38fca1781b..fd73186d6003 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1484,6 +1484,8 @@ static void prepare_playback_urb(struct snd_usb_substream *subs, for (i = 0; i < ctx->packets; i++) { if (ctx->packet_size[i]) counts = ctx->packet_size[i]; + else if (ep->sync_master) + counts = snd_usb_endpoint_slave_next_packet_size(ep); else counts = snd_usb_endpoint_next_packet_size(ep); From b223e40ae75a46e1fb85cad69231cb0c506ed64c Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Thu, 9 Apr 2020 09:59:39 +0200 Subject: [PATCH 061/162] s390/qdio: put thinint indicator after early error [ Upstream commit 75e82bec6b2622c6f455b7a543fb5476a5d0eed7 ] qdio_establish() calls qdio_setup_thinint() via qdio_setup_irq(). If the subsequent qdio_establish_thinint() fails, we miss to put the DSCI again. Thus the DSCI isn't available for re-use. Given enough of such errors, we could end up with having only the shared DSCI available. Merge qdio_setup_thinint() into qdio_establish_thinint(), and deal with such an error internally. Fixes: 779e6e1c724d ("[S390] qdio: new qdio driver.") Signed-off-by: Julian Wiedmann Reviewed-by: Benjamin Block Signed-off-by: Vasily Gorbik Signed-off-by: Sasha Levin --- drivers/s390/cio/qdio.h | 1 - drivers/s390/cio/qdio_setup.c | 1 - drivers/s390/cio/qdio_thinint.c | 14 ++++++++------ 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 29d6b5222f1c..0f8d13288611 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -377,7 +377,6 @@ static inline int multicast_outbound(struct qdio_q *q) extern u64 last_ai_time; /* prototypes for thin interrupt */ -void qdio_setup_thinint(struct qdio_irq *irq_ptr); int qdio_establish_thinint(struct qdio_irq *irq_ptr); void qdio_shutdown_thinint(struct qdio_irq *irq_ptr); void tiqdio_add_input_queues(struct qdio_irq *irq_ptr); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index d0090c5c88e7..a64615a10352 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -479,7 +479,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data) setup_queues(irq_ptr, init_data); setup_qib(irq_ptr, init_data); - qdio_setup_thinint(irq_ptr); set_impl_params(irq_ptr, init_data->qib_param_field_format, init_data->qib_param_field, init_data->input_slib_elements, diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c index 831a3a0a2837..4dc1108069d4 100644 --- a/drivers/s390/cio/qdio_thinint.c +++ b/drivers/s390/cio/qdio_thinint.c @@ -270,17 +270,19 @@ int __init tiqdio_register_thinints(void) int qdio_establish_thinint(struct qdio_irq *irq_ptr) { + int rc; + if (!is_thinint_irq(irq_ptr)) return 0; - return set_subchannel_ind(irq_ptr, 0); -} -void qdio_setup_thinint(struct qdio_irq *irq_ptr) -{ - if (!is_thinint_irq(irq_ptr)) - return; irq_ptr->dsci = get_indicator(); DBF_HEX(&irq_ptr->dsci, sizeof(void *)); + + rc = set_subchannel_ind(irq_ptr, 0); + if (rc) + put_indicator(irq_ptr->dsci); + + return rc; } void qdio_shutdown_thinint(struct qdio_irq *irq_ptr) From e00eda8c9cb93ca1a462de1b513d69d3e2deaa10 Mon Sep 17 00:00:00 2001 From: Raghavendra Rao Ananta Date: Mon, 27 Apr 2020 20:26:01 -0700 Subject: [PATCH 062/162] tty: hvc: Fix data abort due to race in hvc_open [ Upstream commit e2bd1dcbe1aa34ff5570b3427c530e4332ecf0fe ] Potentially, hvc_open() can be called in parallel when two tasks calls open() on /dev/hvcX. In such a scenario, if the hp->ops->notifier_add() callback in the function fails, where it sets the tty->driver_data to NULL, the parallel hvc_open() can see this NULL and cause a memory abort. Hence, serialize hvc_open and check if tty->private_data is NULL before proceeding ahead. The issue can be easily reproduced by launching two tasks simultaneously that does nothing but open() and close() on /dev/hvcX. For example: $ ./simple_open_close /dev/hvc0 & ./simple_open_close /dev/hvc0 & Signed-off-by: Raghavendra Rao Ananta Link: https://lore.kernel.org/r/20200428032601.22127-1-rananta@codeaurora.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/hvc/hvc_console.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index d52221ae1b85..663cbe3669e1 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -88,6 +88,8 @@ static LIST_HEAD(hvc_structs); */ static DEFINE_SPINLOCK(hvc_structs_lock); +/* Mutex to serialize hvc_open */ +static DEFINE_MUTEX(hvc_open_mutex); /* * This value is used to assign a tty->index value to a hvc_struct based * upon order of exposure via hvc_probe(), when we can not match it to @@ -332,16 +334,24 @@ static int hvc_install(struct tty_driver *driver, struct tty_struct *tty) */ static int hvc_open(struct tty_struct *tty, struct file * filp) { - struct hvc_struct *hp = tty->driver_data; + struct hvc_struct *hp; unsigned long flags; int rc = 0; + mutex_lock(&hvc_open_mutex); + + hp = tty->driver_data; + if (!hp) { + rc = -EIO; + goto out; + } + spin_lock_irqsave(&hp->port.lock, flags); /* Check and then increment for fast path open. */ if (hp->port.count++ > 0) { spin_unlock_irqrestore(&hp->port.lock, flags); hvc_kick(); - return 0; + goto out; } /* else count == 0 */ spin_unlock_irqrestore(&hp->port.lock, flags); @@ -369,6 +379,8 @@ static int hvc_open(struct tty_struct *tty, struct file * filp) /* Force wakeup of the polling thread */ hvc_kick(); +out: + mutex_unlock(&hvc_open_mutex); return rc; } From 8bb69793a78668bbb2b73db42ecb688db17bf456 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Fri, 24 Apr 2020 17:19:44 +0100 Subject: [PATCH 063/162] thermal/drivers/ti-soc-thermal: Avoid dereferencing ERR_PTR [ Upstream commit 7440f518dad9d861d76c64956641eeddd3586f75 ] On error the function ti_bandgap_get_sensor_data() returns the error code in ERR_PTR() but we only checked if the return value is NULL or not. And, so we can dereference an error code inside ERR_PTR. While at it, convert a check to IS_ERR_OR_NULL. Signed-off-by: Sudip Mukherjee Reviewed-by: Amit Kucheria Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200424161944.6044-1-sudipm.mukherjee@gmail.com Signed-off-by: Sasha Levin --- drivers/thermal/ti-soc-thermal/ti-thermal-common.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c index c211a8e4a210..fa98c398d70f 100644 --- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c +++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c @@ -183,7 +183,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id, data = ti_bandgap_get_sensor_data(bgp, id); - if (!data || IS_ERR(data)) + if (!IS_ERR_OR_NULL(data)) data = ti_thermal_build_data(bgp, id); if (!data) @@ -210,7 +210,7 @@ int ti_thermal_remove_sensor(struct ti_bandgap *bgp, int id) data = ti_bandgap_get_sensor_data(bgp, id); - if (data && data->ti_thermal) { + if (!IS_ERR_OR_NULL(data) && data->ti_thermal) { if (data->our_zone) thermal_zone_device_unregister(data->ti_thermal); } @@ -276,7 +276,7 @@ int ti_thermal_unregister_cpu_cooling(struct ti_bandgap *bgp, int id) data = ti_bandgap_get_sensor_data(bgp, id); - if (data) { + if (!IS_ERR_OR_NULL(data)) { cpufreq_cooling_unregister(data->cool_dev); cpufreq_cpu_put(data->policy); } From e5dc26148d8a1a194d04979e4cae43b344c845fd Mon Sep 17 00:00:00 2001 From: Matej Dujava Date: Thu, 30 Apr 2020 22:09:24 +0200 Subject: [PATCH 064/162] staging: sm750fb: add missing case while setting FB_VISUAL [ Upstream commit fa90133377f4a7f15a937df6ad55133bb57c5665 ] Switch statement does not contain all cases: 8, 16, 24, 32. This patch will add missing one (24) Fixes: 81dee67e215b ("staging: sm750fb: add sm750 to staging") Signed-off-by: Matej Dujava Link: https://lore.kernel.org/r/1588277366-19354-2-git-send-email-mdujava@kocurkovo.cz Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/sm750fb/sm750.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c index 67207b0554cd..5d6f3686c0de 100644 --- a/drivers/staging/sm750fb/sm750.c +++ b/drivers/staging/sm750fb/sm750.c @@ -899,6 +899,7 @@ static int lynxfb_set_fbinfo(struct fb_info *info, int index) fix->visual = FB_VISUAL_PSEUDOCOLOR; break; case 16: + case 24: case 32: fix->visual = FB_VISUAL_TRUECOLOR; break; From 359af0d4f8b5343ca07e58cd9abe6cc740fe589e Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 27 Apr 2020 19:49:22 +0100 Subject: [PATCH 065/162] i2c: pxa: fix i2c_pxa_scream_blue_murder() debug output [ Upstream commit 88b73ee7ca4c90baf136ed5a8377fc5a9b73ac08 ] The IRQ log output is supposed to appear on a single line. However, commit 3a2dc1677b60 ("i2c: pxa: Update debug function to dump more info on error") resulted in it being printed one-entry-per-line, which is excessively long. Fixing this is not a trivial matter; using pr_cont() doesn't work as the previous dev_dbg() may not have been compiled in, or may be dynamic. Since the rest of this function output is at error level, and is also debug output, promote this to error level as well to avoid this problem. Reduce the number of always zero prefix digits to save screen real- estate. Signed-off-by: Russell King Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-pxa.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index ecc84aea5131..e300f9530f19 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -315,11 +315,10 @@ static void i2c_pxa_scream_blue_murder(struct pxa_i2c *i2c, const char *why) dev_err(dev, "IBMR: %08x IDBR: %08x ICR: %08x ISR: %08x\n", readl(_IBMR(i2c)), readl(_IDBR(i2c)), readl(_ICR(i2c)), readl(_ISR(i2c))); - dev_dbg(dev, "log: "); + dev_err(dev, "log:"); for (i = 0; i < i2c->irqlogidx; i++) - pr_debug("[%08x:%08x] ", i2c->isrlog[i], i2c->icrlog[i]); - - pr_debug("\n"); + pr_cont(" [%03x:%05x]", i2c->isrlog[i], i2c->icrlog[i]); + pr_cont("\n"); } #else /* ifdef DEBUG */ From 44a32bc22d699e79ad2a0dbea9886684bf66a2d1 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 28 Apr 2020 18:40:50 +0000 Subject: [PATCH 066/162] serial: amba-pl011: Make sure we initialize the port.lock spinlock [ Upstream commit 8508f4cba308f785b2fd4b8c38849c117b407297 ] Valentine reported seeing: [ 3.626638] INFO: trying to register non-static key. [ 3.626639] the code is fine but needs lockdep annotation. [ 3.626640] turning off the locking correctness validator. [ 3.626644] CPU: 7 PID: 51 Comm: kworker/7:1 Not tainted 5.7.0-rc2-00115-g8c2e9790f196 #116 [ 3.626646] Hardware name: HiKey960 (DT) [ 3.626656] Workqueue: events deferred_probe_work_func [ 3.632476] sd 0:0:0:0: [sda] Optimal transfer size 8192 bytes not a multiple of physical block size (16384 bytes) [ 3.640220] Call trace: [ 3.640225] dump_backtrace+0x0/0x1b8 [ 3.640227] show_stack+0x20/0x30 [ 3.640230] dump_stack+0xec/0x158 [ 3.640234] register_lock_class+0x598/0x5c0 [ 3.640235] __lock_acquire+0x80/0x16c0 [ 3.640236] lock_acquire+0xf4/0x4a0 [ 3.640241] _raw_spin_lock_irqsave+0x70/0xa8 [ 3.640245] uart_add_one_port+0x388/0x4b8 [ 3.640248] pl011_register_port+0x70/0xf0 [ 3.640250] pl011_probe+0x184/0x1b8 [ 3.640254] amba_probe+0xdc/0x180 [ 3.640256] really_probe+0xe0/0x338 [ 3.640257] driver_probe_device+0x60/0xf8 [ 3.640259] __device_attach_driver+0x8c/0xd0 [ 3.640260] bus_for_each_drv+0x84/0xd8 [ 3.640261] __device_attach+0xe4/0x140 [ 3.640263] device_initial_probe+0x1c/0x28 [ 3.640265] bus_probe_device+0xa4/0xb0 [ 3.640266] deferred_probe_work_func+0x7c/0xb8 [ 3.640269] process_one_work+0x2c0/0x768 [ 3.640271] worker_thread+0x4c/0x498 [ 3.640272] kthread+0x14c/0x158 [ 3.640275] ret_from_fork+0x10/0x1c Which seems to be due to the fact that after allocating the uap structure, nothing initializes the spinlock. Its a little confusing, as uart_port_spin_lock_init() is one place where the lock is supposed to be initialized, but it has an exception for the case where the port is a console. This makes it seem like a deeper fix is needed to properly register the console, but I'm not sure what that entails, and Andy suggested that this approach is less invasive. Thus, this patch resolves the issue by initializing the spinlock in the driver, and resolves the resulting warning. Cc: Andy Shevchenko Cc: Russell King Cc: Jiri Slaby Cc: linux-serial@vger.kernel.org Reported-by: Valentin Schneider Reviewed-by: Andy Shevchenko Signed-off-by: John Stultz Reviewed-and-tested-by: Valentin Schneider Link: https://lore.kernel.org/r/20200428184050.6501-1-john.stultz@linaro.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/amba-pl011.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 637f72fb6427..e55b55633721 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2605,6 +2605,7 @@ static int pl011_setup_port(struct device *dev, struct uart_amba_port *uap, uap->port.fifosize = uap->fifosize; uap->port.flags = UPF_BOOT_AUTOCONF; uap->port.line = index; + spin_lock_init(&uap->port.lock); amba_ports[index] = uap; From 790c37291cb584cc78ffd80f12640e4ef2171868 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Wed, 8 Apr 2020 14:40:03 -0700 Subject: [PATCH 067/162] drivers: base: Fix NULL pointer exception in __platform_driver_probe() if a driver developer is foolish [ Upstream commit 388bcc6ecc609fca1b4920de7dc3806c98ec535e ] If platform bus driver registration is failed then, accessing platform bus spin lock (&drv->driver.bus->p->klist_drivers.k_lock) in __platform_driver_probe() without verifying the return value __platform_driver_register() can lead to NULL pointer exception. So check the return value before attempting the spin lock. One such example is below: For a custom usecase, I have intentionally failed the platform bus registration and I expected all the platform device/driver registrations to fail gracefully. But I came across this panic issue. [ 1.331067] BUG: kernel NULL pointer dereference, address: 00000000000000c8 [ 1.331118] #PF: supervisor write access in kernel mode [ 1.331163] #PF: error_code(0x0002) - not-present page [ 1.331208] PGD 0 P4D 0 [ 1.331233] Oops: 0002 [#1] PREEMPT SMP [ 1.331268] CPU: 3 PID: 1 Comm: swapper/0 Tainted: G W 5.6.0-00049-g670d35fb0144 #165 [ 1.331341] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 [ 1.331406] RIP: 0010:_raw_spin_lock+0x15/0x30 [ 1.331588] RSP: 0000:ffffc9000001be70 EFLAGS: 00010246 [ 1.331632] RAX: 0000000000000000 RBX: 00000000000000c8 RCX: 0000000000000001 [ 1.331696] RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000000 [ 1.331754] RBP: 00000000ffffffed R08: 0000000000000501 R09: 0000000000000001 [ 1.331817] R10: ffff88817abcc520 R11: 0000000000000670 R12: 00000000ffffffed [ 1.331881] R13: ffffffff82dbc268 R14: ffffffff832f070a R15: 0000000000000000 [ 1.331945] FS: 0000000000000000(0000) GS:ffff88817bd80000(0000) knlGS:0000000000000000 [ 1.332008] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1.332062] CR2: 00000000000000c8 CR3: 000000000681e001 CR4: 00000000003606e0 [ 1.332126] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1.332189] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1.332252] Call Trace: [ 1.332281] __platform_driver_probe+0x92/0xee [ 1.332323] ? rtc_dev_init+0x2b/0x2b [ 1.332358] cmos_init+0x37/0x67 [ 1.332396] do_one_initcall+0x7d/0x168 [ 1.332428] kernel_init_freeable+0x16c/0x1c9 [ 1.332473] ? rest_init+0xc0/0xc0 [ 1.332508] kernel_init+0x5/0x100 [ 1.332543] ret_from_fork+0x1f/0x30 [ 1.332579] CR2: 00000000000000c8 [ 1.332616] ---[ end trace 3bd87f12e9010b87 ]--- [ 1.333549] note: swapper/0[1] exited with preempt_count 1 [ 1.333592] Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009 [ 1.333736] Kernel Offset: disabled Note, this can only be triggered if a driver errors out from this call, which should never happen. If it does, the driver needs to be fixed. Signed-off-by: Kuppuswamy Sathyanarayanan Link: https://lore.kernel.org/r/20200408214003.3356-1-sathyanarayanan.kuppuswamy@linux.intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/platform.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index bcb6519fe211..0ee3cab88f70 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -702,6 +702,8 @@ int __init_or_module __platform_driver_probe(struct platform_driver *drv, /* temporary section violation during probe() */ drv->probe = probe; retval = code = __platform_driver_register(drv, module); + if (retval) + return retval; /* * Fixup that section violation, being paranoid about code scanning From 4cc6125d46ea6ee5c05605d5fb750dac2877fc39 Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Fri, 4 Oct 2019 14:29:41 +0100 Subject: [PATCH 068/162] PCI: rcar: Fix incorrect programming of OB windows [ Upstream commit 2b9f217433e31d125fb697ca7974d3de3ecc3e92 ] The outbound windows (PCIEPAUR(x), PCIEPALR(x)) describe a mapping between a CPU address (which is determined by the window number 'x') and a programmed PCI address - Thus allowing the controller to translate CPU accesses into PCI accesses. However the existing code incorrectly writes the CPU address - lets fix this by writing the PCI address instead. For memory transactions, existing DT users describe a 1:1 identity mapping and thus this change should have no effect. However the same isn't true for I/O. Link: https://lore.kernel.org/r/20191004132941.6660-1-andrew.murray@arm.com Fixes: c25da4778803 ("PCI: rcar: Add Renesas R-Car PCIe driver") Tested-by: Marek Vasut Signed-off-by: Andrew Murray Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Vasut Signed-off-by: Sasha Levin --- drivers/pci/host/pcie-rcar.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c index 2b0a1f3b8265..0077afca2493 100644 --- a/drivers/pci/host/pcie-rcar.c +++ b/drivers/pci/host/pcie-rcar.c @@ -328,11 +328,12 @@ static struct pci_ops rcar_pcie_ops = { }; static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie, - struct resource *res) + struct resource_entry *window) { /* Setup PCIe address space mappings for each resource */ resource_size_t size; resource_size_t res_start; + struct resource *res = window->res; u32 mask; rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win)); @@ -346,9 +347,9 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie, rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win)); if (res->flags & IORESOURCE_IO) - res_start = pci_pio_to_address(res->start); + res_start = pci_pio_to_address(res->start) - window->offset; else - res_start = res->start; + res_start = res->start - window->offset; rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPAUR(win)); rcar_pci_write_reg(pcie, lower_32_bits(res_start) & ~0x7F, @@ -377,7 +378,7 @@ static int rcar_pcie_setup(struct list_head *resource, struct rcar_pcie *pci) switch (resource_type(res)) { case IORESOURCE_IO: case IORESOURCE_MEM: - rcar_pcie_setup_window(i, pci, res); + rcar_pcie_setup_window(i, pci, win); i++; break; case IORESOURCE_BUS: From 02c7838201e940e897617bd4bb035b525a9f5d98 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Wed, 6 May 2020 01:34:21 +0800 Subject: [PATCH 069/162] PCI/ASPM: Allow ASPM on links to PCIe-to-PCI/PCI-X Bridges [ Upstream commit 66ff14e59e8a30690755b08bc3042359703fb07a ] 7d715a6c1ae5 ("PCI: add PCI Express ASPM support") added the ability for Linux to enable ASPM, but for some undocumented reason, it didn't enable ASPM on links where the downstream component is a PCIe-to-PCI/PCI-X Bridge. Remove this exclusion so we can enable ASPM on these links. The Dell OptiPlex 7080 mentioned in the bugzilla has a TI XIO2001 PCIe-to-PCI Bridge. Enabling ASPM on the link leading to it allows the Intel SoC to enter deeper Package C-states, which is a significant power savings. [bhelgaas: commit log] Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=207571 Link: https://lore.kernel.org/r/20200505173423.26968-1-kai.heng.feng@canonical.com Signed-off-by: Kai-Heng Feng Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg Signed-off-by: Sasha Levin --- drivers/pci/pcie/aspm.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 400031622b76..04d5c62588b7 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -584,16 +584,6 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) /* Setup initial capable state. Will be updated later */ link->aspm_capable = link->aspm_support; - /* - * If the downstream component has pci bridge function, don't - * do ASPM for now. - */ - list_for_each_entry(child, &linkbus->devices, bus_list) { - if (pci_pcie_type(child) == PCI_EXP_TYPE_PCI_BRIDGE) { - link->aspm_disable = ASPM_STATE_ALL; - break; - } - } /* Get and check endpoint acceptable latencies */ list_for_each_entry(child, &linkbus->devices, bus_list) { From 2125ba574dd7757291929705e0212792e71f7092 Mon Sep 17 00:00:00 2001 From: Viacheslav Dubeyko Date: Fri, 10 Apr 2020 11:07:08 +0300 Subject: [PATCH 070/162] scsi: qla2xxx: Fix warning after FC target reset [ Upstream commit f839544ccff60cbe534282aac68858fc3fb278ca ] Currently, FC target reset finishes with the warning message: [84010.596893] ------------[ cut here ]------------ [84010.596917] WARNING: CPU: 238 PID: 279973 at ../drivers/scsi/qla2xxx/qla_target.c:6644 qlt_enable_vha+0x1d0/0x260 [qla2xxx] [84010.596918] Modules linked in: vrf af_packet 8021q garp mrp stp llc netlink_diag target_tatlin_tblock(OEX) dm_ec(OEX) ttln_rdma(OEX) dm_frontend(OEX) nvme_rdma nvmet tcm_qla2xxx iscsi_target_mod target_core_mod at24 nvmem_core pnv_php ipmi_watchdog ipmi_ssif vmx_crypto gf128mul crct10dif_vpmsum qla2xxx rpcrdma nvme_fc powernv_flash(X) nvme_fabrics uio_pdrv_genirq mtd rtc_opal(X) ibmpowernv(X) opal_prd(X) uio scsi_transport_fc i2c_opal(X) ses enclosure ipmi_poweroff ast i2c_algo_bit ttm bmc_mcu(OEX) drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm drm_panel_orientation_quirks agpgart nfsd auth_rpcgss nfs_acl ipmi_powernv(X) lockd ipmi_devintf ipmi_msghandler grace dummy ext4 crc16 jbd2 mbcache sd_mod rdma_ucm ib_iser rdma_cm ib_umad iw_cm ib_ipoib libiscsi scsi_transport_iscsi ib_cm [84010.596975] configfs mlx5_ib ib_uverbs ib_core mlx5_core crc32c_vpmsum xhci_pci xhci_hcd mpt3sas(OEX) tg3 usbcore mlxfw tls raid_class libphy scsi_transport_sas devlink ptp pps_core nvme nvme_core sunrpc dm_mirror dm_region_hash dm_log sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua scsi_mod autofs4 [84010.597001] Supported: Yes, External [84010.597004] CPU: 238 PID: 279973 Comm: bash Tainted: G OE 4.12.14-197.29-default #1 SLE15-SP1 [84010.597006] task: c000000a104c0000 task.stack: c000000b52188000 [84010.597007] NIP: d00000001ffd7f78 LR: d00000001ffd7f6c CTR: c0000000001676c0 [84010.597008] REGS: c000000b5218b910 TRAP: 0700 Tainted: G OE (4.12.14-197.29-default) [84010.597008] MSR: 900000010282b033 [84010.597015] CR: 48242424 XER: 00000000 [84010.597016] CFAR: d00000001ff45d08 SOFTE: 1 GPR00: d00000001ffd7f6c c000000b5218bb90 d00000002001b228 0000000000000102 GPR04: 0000000000000001 0000000000000001 00013d91ed0a5e2d 0000000000000000 GPR08: c000000007793300 0000000000000000 0000000000000000 c000000a086e7818 GPR12: 0000000000002200 c000000007793300 0000000000000000 000000012bc937c0 GPR16: 000000012bbf7ed0 0000000000000000 000000012bc3dd10 0000000000000000 GPR20: 000000012bc4db28 0000010036442810 000000012bc97828 000000012bc96c70 GPR24: 00000100365b1550 0000000000000000 00000100363f3d80 c000000be20d3080 GPR28: c000000bda7eae00 c000000be20db7e8 c000000be20d3778 c000000be20db7e8 [84010.597042] NIP [d00000001ffd7f78] qlt_enable_vha+0x1d0/0x260 [qla2xxx] [84010.597051] LR [d00000001ffd7f6c] qlt_enable_vha+0x1c4/0x260 [qla2xxx] [84010.597051] Call Trace: [84010.597061] [c000000b5218bb90] [d00000001ffd7f6c] qlt_enable_vha+0x1c4/0x260 [qla2xxx] (unreliable) [84010.597064] [c000000b5218bc20] [d000000009820b6c] tcm_qla2xxx_tpg_enable_store+0xc4/0x130 [tcm_qla2xxx] [84010.597067] [c000000b5218bcb0] [d0000000185d0e68] configfs_write_file+0xd0/0x190 [configfs] [84010.597072] [c000000b5218bd00] [c0000000003d0edc] __vfs_write+0x3c/0x1e0 [84010.597074] [c000000b5218bd90] [c0000000003d2ea8] vfs_write+0xd8/0x220 [84010.597076] [c000000b5218bde0] [c0000000003d4ddc] SyS_write+0x6c/0x110 [84010.597079] [c000000b5218be30] [c00000000000b188] system_call+0x3c/0x130 [84010.597080] Instruction dump: [84010.597082] 7d0050a8 7d084b78 7d0051ad 40c2fff4 7fa3eb78 4bf73965 60000000 7fa3eb78 [84010.597086] 4bf6dcd9 60000000 2fa30000 419eff40 <0fe00000> 4bffff38 e95f0058 a12a0180 [84010.597090] ---[ end trace e32abaf6e6fee826 ]--- To reproduce: echo 0x7fffffff > /sys/module/qla2xxx/parameters/logging modprobe target_core_mod modprobe tcm_qla2xxx mkdir /sys/kernel/config/target/qla2xxx mkdir /sys/kernel/config/target/qla2xxx/ mkdir /sys/kernel/config/target/qla2xxx//tpgt_1 echo 1 > /sys/kernel/config/target/qla2xxx//tpgt_1/enable echo 0 > /sys/kernel/config/target/qla2xxx//tpgt_1/enable echo 1 > /sys/kernel/config/target/qla2xxx//tpgt_1/enable SYSTEM START kernel: pid 327:drivers/scsi/qla2xxx/qla_init.c:2174 qla2x00_initialize_adapter(): vha->flags.online 0x0 <...> kernel: pid 327:drivers/scsi/qla2xxx/qla_os.c:3444 qla2x00_probe_one(): vha->flags.online 0x1 echo 1 > /sys/kernel/config/target/qla2xxx/21:00:00:24:ff:86:a6:2a/tpgt_1/enable kernel: pid 348:drivers/scsi/qla2xxx/qla_init.c:6641 qla2x00_abort_isp_cleanup(): vha->flags.online 0x0, ISP_ABORT_NEEDED 0x0 <...> kernel: pid 348:drivers/scsi/qla2xxx/qla_init.c:6998 qla2x00_restart_isp(): vha->flags.online 0x0 echo 0 > /sys/kernel/config/target/qla2xxx/21:00:00:24:ff:86:a6:2a/tpgt_1/enable kernel: pid 348:drivers/scsi/qla2xxx/qla_init.c:6641 qla2x00_abort_isp_cleanup(): vha->flags.online 0x0, ISP_ABORT_NEEDED 0x0 <...> kernel: pid 1404:drivers/scsi/qla2xxx/qla_os.c:1107 qla2x00_wait_for_hba_online(): base_vha->flags.online 0x0 echo 1 > /sys/kernel/config/target/qla2xxx/21:00:00:24:ff:86:a6:2a/tpgt_1/enable kernel: pid 1404:drivers/scsi/qla2xxx/qla_os.c:1107 qla2x00_wait_for_hba_online(): base_vha->flags.online 0x0 kernel: -----------[ cut here ]----------- kernel: WARNING: CPU: 1 PID: 1404 at drivers/scsi/qla2xxx/qla_target.c:6654 qlt_enable_vha+0x1e0/0x280 [qla2xxx] The issue happens because no real ISP reset is executed. The qla2x00_abort_isp(scsi_qla_host_t *vha) function expects that vha->flags.online will be not zero for ISP reset procedure. This patch sets vha->flags.online to 1 before calling ->abort_isp() for starting the ISP reset. Link: https://lore.kernel.org/r/1d7b21bf9f7676643239eb3d60eaca7cfa505cf0.camel@yadro.com Reviewed-by: Roman Bolshakov Signed-off-by: Viacheslav Dubeyko Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_os.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index d4024015f859..ea60c6e603c0 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -5824,6 +5824,7 @@ qla2x00_do_dpc(void *data) if (do_reset && !(test_and_set_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags))) { + base_vha->flags.online = 1; ql_dbg(ql_dbg_dpc, base_vha, 0x4007, "ISP abort scheduled.\n"); if (ha->isp_ops->abort_isp(base_vha)) { From 9ff759a7f9ab8c450d3b04de685ef4c37b7ad0fc Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 9 May 2020 10:23:23 +0200 Subject: [PATCH 071/162] power: supply: lp8788: Fix an error handling path in 'lp8788_charger_probe()' [ Upstream commit 934ed3847a4ebc75b655659c4d2349ba4337941c ] In the probe function, in case of error, resources allocated in 'lp8788_setup_adc_channel()' must be released. This can be achieved easily by using the devm_ variant of 'iio_channel_get()'. This has the extra benefit to simplify the remove function and to axe the 'lp8788_release_adc_channel()' function which is now useless. Fixes: 98a276649358 ("power_supply: Add new lp8788 charger driver") Signed-off-by: Christophe JAILLET Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/lp8788-charger.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/drivers/power/supply/lp8788-charger.c b/drivers/power/supply/lp8788-charger.c index 0f3432795f3c..b8f7dac7ac3f 100644 --- a/drivers/power/supply/lp8788-charger.c +++ b/drivers/power/supply/lp8788-charger.c @@ -600,27 +600,14 @@ static void lp8788_setup_adc_channel(struct device *dev, return; /* ADC channel for battery voltage */ - chan = iio_channel_get(dev, pdata->adc_vbatt); + chan = devm_iio_channel_get(dev, pdata->adc_vbatt); pchg->chan[LP8788_VBATT] = IS_ERR(chan) ? NULL : chan; /* ADC channel for battery temperature */ - chan = iio_channel_get(dev, pdata->adc_batt_temp); + chan = devm_iio_channel_get(dev, pdata->adc_batt_temp); pchg->chan[LP8788_BATT_TEMP] = IS_ERR(chan) ? NULL : chan; } -static void lp8788_release_adc_channel(struct lp8788_charger *pchg) -{ - int i; - - for (i = 0; i < LP8788_NUM_CHG_ADC; i++) { - if (!pchg->chan[i]) - continue; - - iio_channel_release(pchg->chan[i]); - pchg->chan[i] = NULL; - } -} - static ssize_t lp8788_show_charger_status(struct device *dev, struct device_attribute *attr, char *buf) { @@ -747,7 +734,6 @@ static int lp8788_charger_remove(struct platform_device *pdev) lp8788_irq_unregister(pdev, pchg); sysfs_remove_group(&pdev->dev.kobj, &lp8788_attr_group); lp8788_psy_unregister(pchg); - lp8788_release_adc_channel(pchg); return 0; } From eb6a01ad9edeab2e74005e4cb400ff4b32f0bee1 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sun, 29 Mar 2020 18:15:44 +0200 Subject: [PATCH 072/162] power: supply: smb347-charger: IRQSTAT_D is volatile [ Upstream commit c32ea07a30630ace950e07ffe7a18bdcc25898e1 ] Fix failure when USB cable is connected: smb347 2-006a: reading IRQSTAT_D failed Fixes: 1502cfe19bac ("smb347-charger: Fix battery status reporting logic for charger faults") Tested-by: David Heidelberg Signed-off-by: Dmitry Osipenko Signed-off-by: David Heidelberg Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/smb347-charger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/power/supply/smb347-charger.c b/drivers/power/supply/smb347-charger.c index 072c5189bd6d..0655dbdc7000 100644 --- a/drivers/power/supply/smb347-charger.c +++ b/drivers/power/supply/smb347-charger.c @@ -1141,6 +1141,7 @@ static bool smb347_volatile_reg(struct device *dev, unsigned int reg) switch (reg) { case IRQSTAT_A: case IRQSTAT_C: + case IRQSTAT_D: case IRQSTAT_E: case IRQSTAT_F: case STAT_A: From 4c5a89f8ae5a0bbc83bd0a1a9ed57a2927e221e4 Mon Sep 17 00:00:00 2001 From: Suganath Prabu S Date: Fri, 8 May 2020 07:07:38 -0400 Subject: [PATCH 073/162] scsi: mpt3sas: Fix double free warnings [ Upstream commit cbbfdb2a2416c9f0cde913cf09670097ac281282 ] Fix following warning from Smatch static analyser: drivers/scsi/mpt3sas/mpt3sas_base.c:5256 _base_allocate_memory_pools() warn: 'ioc->hpr_lookup' double freed drivers/scsi/mpt3sas/mpt3sas_base.c:5256 _base_allocate_memory_pools() warn: 'ioc->internal_lookup' double freed Link: https://lore.kernel.org/r/20200508110738.30732-1-suganath-prabu.subramani@broadcom.com Reported-by: Dan Carpenter Signed-off-by: Suganath Prabu S Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_base.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 817a7963a038..556971c5f0b0 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3263,7 +3263,9 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) ioc->scsi_lookup = NULL; } kfree(ioc->hpr_lookup); + ioc->hpr_lookup = NULL; kfree(ioc->internal_lookup); + ioc->internal_lookup = NULL; if (ioc->chain_lookup) { for (i = 0; i < ioc->chain_depth; i++) { if (ioc->chain_lookup[i].chain_buffer) From 6a1fa20e971f84f30c092ff41bfc081fc5f07281 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 7 May 2020 23:34:28 +0200 Subject: [PATCH 074/162] dlm: remove BUG() before panic() [ Upstream commit fe204591cc9480347af7d2d6029b24a62e449486 ] Building a kernel with clang sometimes fails with an objtool error in dlm: fs/dlm/lock.o: warning: objtool: revert_lock_pc()+0xbd: can't find jump dest instruction at .text+0xd7fc The problem is that BUG() never returns and the compiler knows that anything after it is unreachable, however the panic still emits some code that does not get fully eliminated. Having both BUG() and panic() is really pointless as the BUG() kills the current process and the subsequent panic() never hits. In most cases, we probably don't really want either and should replace the DLM_ASSERT() statements with WARN_ON(), as has been done for some of them. Remove the BUG() here so the user at least sees the panic message and we can reliably build randconfig kernels. Fixes: e7fd41792fc0 ("[DLM] The core of the DLM for GFS2/CLVM") Cc: Josh Poimboeuf Cc: clang-built-linux@googlegroups.com Signed-off-by: Arnd Bergmann Signed-off-by: David Teigland Signed-off-by: Sasha Levin --- fs/dlm/dlm_internal.h | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 748e8d59e611..cb287df13a7a 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -99,7 +99,6 @@ do { \ __LINE__, __FILE__, #x, jiffies); \ {do} \ printk("\n"); \ - BUG(); \ panic("DLM: Record message above and reboot.\n"); \ } \ } From fa2ddb114121654b3fc660eb26ffb6b08936bd5c Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 29 Apr 2020 16:13:39 +0300 Subject: [PATCH 075/162] clk: ti: composite: fix memory leak [ Upstream commit c7c1cbbc9217ebb5601b88d138d4a5358548de9d ] The parent_names is never released for a component clock definition, causing some memory leak. Fix by releasing it once it is no longer needed. Reported-by: Tomi Valkeinen Signed-off-by: Tero Kristo Link: https://lkml.kernel.org/r/20200429131341.4697-2-t-kristo@ti.com Acked-by: Tony Lindgren Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/ti/composite.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/ti/composite.c b/drivers/clk/ti/composite.c index beea89463ca2..4ea5c08a1eb6 100644 --- a/drivers/clk/ti/composite.c +++ b/drivers/clk/ti/composite.c @@ -240,6 +240,7 @@ cleanup: if (!cclk->comp_clks[i]) continue; list_del(&cclk->comp_clks[i]->link); + kfree(cclk->comp_clks[i]->parent_names); kfree(cclk->comp_clks[i]); } From a2ef4a98cf03c9262cc623dc7a998c7786a4e6b7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 13 May 2020 17:38:58 -0500 Subject: [PATCH 076/162] PCI: Fix pci_register_host_bridge() device_register() error handling [ Upstream commit 1b54ae8327a4d630111c8d88ba7906483ec6010b ] If device_register() has an error, we should bail out of pci_register_host_bridge() rather than continuing on. Fixes: 37d6a0a6f470 ("PCI: Add pci_register_host_bridge() interface") Link: https://lore.kernel.org/r/20200513223859.11295-1-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Bjorn Helgaas Reviewed-by: Lorenzo Pieralisi Reviewed-by: Arnd Bergmann Signed-off-by: Sasha Levin --- drivers/pci/probe.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 31cc04aeaaaa..55ece07e584a 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -792,9 +792,10 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) goto free; err = device_register(&bridge->dev); - if (err) + if (err) { put_device(&bridge->dev); - + goto free; + } bus->bridge = get_device(&bridge->dev); device_enable_async_suspend(bus->bridge); pci_set_bus_of_node(bus); From 44c68ccdc80dab817a8e2cf935be5dbbbbf64c07 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Tue, 12 May 2020 13:53:22 +0200 Subject: [PATCH 077/162] tty: n_gsm: Fix SOF skipping [ Upstream commit 84d6f81c1fb58b56eba81ff0a36cf31946064b40 ] For at least some modems like the TELIT LE910, skipping SOF makes transfers blocking indefinitely after a short amount of data transferred. Given the small improvement provided by skipping the SOF (just one byte on about 100 bytes), it seems better to completely remove this "feature" than make it optional. Fixes: e1eaea46bb40 ("tty: n_gsm line discipline") Signed-off-by: Gregory CLEMENT Link: https://lore.kernel.org/r/20200512115323.1447922-3-gregory.clement@bootlin.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/n_gsm.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index f46bd1af7a10..eabdcfa414aa 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -681,7 +681,6 @@ static void gsm_data_kick(struct gsm_mux *gsm) { struct gsm_msg *msg, *nmsg; int len; - int skip_sof = 0; list_for_each_entry_safe(msg, nmsg, &gsm->tx_list, list) { if (gsm->constipated && msg->addr) @@ -703,15 +702,10 @@ static void gsm_data_kick(struct gsm_mux *gsm) print_hex_dump_bytes("gsm_data_kick: ", DUMP_PREFIX_OFFSET, gsm->txframe, len); - - if (gsm->output(gsm, gsm->txframe + skip_sof, - len - skip_sof) < 0) + if (gsm->output(gsm, gsm->txframe, len) < 0) break; /* FIXME: Can eliminate one SOF in many more cases */ gsm->tx_bytes -= msg->len; - /* For a burst of frames skip the extra SOF within the - burst */ - skip_sof = 1; list_del(&msg->list); kfree(msg); From 5665eea71f06ea57487547b2cddd856a2cf0c486 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Tue, 12 May 2020 13:53:23 +0200 Subject: [PATCH 078/162] tty: n_gsm: Fix waking up upper tty layer when room available [ Upstream commit 01dbb362f0a114fbce19c8abe4cd6f4710e934d5 ] Warn the upper layer when n_gms is ready to receive data again. Without this the associated virtual tty remains blocked indefinitely. Fixes: e1eaea46bb40 ("tty: n_gsm line discipline") Signed-off-by: Gregory CLEMENT Link: https://lore.kernel.org/r/20200512115323.1447922-4-gregory.clement@bootlin.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/n_gsm.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index eabdcfa414aa..e7417eac3f21 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -677,7 +677,7 @@ static struct gsm_msg *gsm_data_alloc(struct gsm_mux *gsm, u8 addr, int len, * FIXME: lock against link layer control transmissions */ -static void gsm_data_kick(struct gsm_mux *gsm) +static void gsm_data_kick(struct gsm_mux *gsm, struct gsm_dlci *dlci) { struct gsm_msg *msg, *nmsg; int len; @@ -709,6 +709,24 @@ static void gsm_data_kick(struct gsm_mux *gsm) list_del(&msg->list); kfree(msg); + + if (dlci) { + tty_port_tty_wakeup(&dlci->port); + } else { + int i = 0; + + for (i = 0; i < NUM_DLCI; i++) { + struct gsm_dlci *dlci; + + dlci = gsm->dlci[i]; + if (dlci == NULL) { + i++; + continue; + } + + tty_port_tty_wakeup(&dlci->port); + } + } } } @@ -760,7 +778,7 @@ static void __gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg) /* Add to the actual output queue */ list_add_tail(&msg->list, &gsm->tx_list); gsm->tx_bytes += msg->len; - gsm_data_kick(gsm); + gsm_data_kick(gsm, dlci); } /** @@ -1221,7 +1239,7 @@ static void gsm_control_message(struct gsm_mux *gsm, unsigned int command, gsm_control_reply(gsm, CMD_FCON, NULL, 0); /* Kick the link in case it is idling */ spin_lock_irqsave(&gsm->tx_lock, flags); - gsm_data_kick(gsm); + gsm_data_kick(gsm, NULL); spin_unlock_irqrestore(&gsm->tx_lock, flags); break; case CMD_FCOFF: @@ -2420,7 +2438,7 @@ static void gsmld_write_wakeup(struct tty_struct *tty) /* Queue poll */ clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); spin_lock_irqsave(&gsm->tx_lock, flags); - gsm_data_kick(gsm); + gsm_data_kick(gsm, NULL); if (gsm->tx_bytes < TX_THRESH_LO) { gsm_dlci_data_sweep(gsm); } From 1a5dfc48f7d05b23d321d2a975c3b398b9616d00 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 8 May 2020 14:33:58 +1000 Subject: [PATCH 079/162] powerpc/pseries/ras: Fix FWNMI_VALID off by one [ Upstream commit deb70f7a35a22dffa55b2c3aac71bc6fb0f486ce ] This was discovered developing qemu fwnmi sreset support. This off-by-one bug means the last 16 bytes of the rtas area can not be used for a 16 byte save area. It's not a serious bug, and QEMU implementation has to retain a workaround for old kernels, but it's good to tighten it. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Acked-by: Mahesh Salgaonkar Link: https://lore.kernel.org/r/20200508043408.886394-7-npiggin@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/ras.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 99d1152ae224..5ec935521204 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -325,10 +325,11 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) /* * Some versions of FWNMI place the buffer inside the 4kB page starting at * 0x7000. Other versions place it inside the rtas buffer. We check both. + * Minimum size of the buffer is 16 bytes. */ #define VALID_FWNMI_BUFFER(A) \ - ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ - (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) + ((((A) >= 0x7000) && ((A) <= 0x8000 - 16)) || \ + (((A) >= rtas.base) && ((A) <= (rtas.base + rtas.size - 16)))) /* * Get the error information for errors coming through the From 3fc44e3bca97e6b4999fef7b3385311343410229 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Sat, 9 May 2020 18:58:32 +0000 Subject: [PATCH 080/162] powerpc/ps3: Fix kexec shutdown hang [ Upstream commit 126554465d93b10662742128918a5fc338cda4aa ] The ps3_mm_region_destroy() and ps3_mm_vas_destroy() routines are called very late in the shutdown via kexec's mmu_cleanup_all routine. By the time mmu_cleanup_all runs it is too late to use udbg_printf, and calling it will cause PS3 systems to hang. Remove all debugging statements from ps3_mm_region_destroy() and ps3_mm_vas_destroy() and replace any error reporting with calls to lv1_panic. With this change builds with 'DEBUG' defined will not cause kexec reboots to hang, and builds with 'DEBUG' defined or not will end in lv1_panic if an error is encountered. Signed-off-by: Geoff Levand Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/7325c4af2b4c989c19d6a26b90b1fec9c0615ddf.1589049250.git.geoff@infradead.org Signed-off-by: Sasha Levin --- arch/powerpc/platforms/ps3/mm.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c index b0f34663b1ae..19bae78b1f25 100644 --- a/arch/powerpc/platforms/ps3/mm.c +++ b/arch/powerpc/platforms/ps3/mm.c @@ -212,13 +212,14 @@ void ps3_mm_vas_destroy(void) { int result; - DBG("%s:%d: map.vas_id = %llu\n", __func__, __LINE__, map.vas_id); - if (map.vas_id) { result = lv1_select_virtual_address_space(0); - BUG_ON(result); - result = lv1_destruct_virtual_address_space(map.vas_id); - BUG_ON(result); + result += lv1_destruct_virtual_address_space(map.vas_id); + + if (result) { + lv1_panic(0); + } + map.vas_id = 0; } } @@ -316,19 +317,20 @@ static void ps3_mm_region_destroy(struct mem_region *r) int result; if (!r->destroy) { - pr_info("%s:%d: Not destroying high region: %llxh %llxh\n", - __func__, __LINE__, r->base, r->size); return; } - DBG("%s:%d: r->base = %llxh\n", __func__, __LINE__, r->base); - if (r->base) { result = lv1_release_memory(r->base); - BUG_ON(result); + + if (result) { + lv1_panic(0); + } + r->size = r->base = r->offset = 0; map.total = map.rm.size; } + ps3_mm_set_repository_highmem(NULL); } From 26340f8f0dac9549720b1023b0cd9345750798e3 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 8 Apr 2020 11:45:28 -0600 Subject: [PATCH 081/162] vfio-pci: Mask cap zero [ Upstream commit bc138db1b96264b9c1779cf18d5a3b186aa90066 ] The PCI Code and ID Assignment Specification changed capability ID 0 from reserved to a NULL capability in the v1.1 revision. The NULL capability is defined to include only the 16-bit capability header, ie. only the ID and next pointer. Unfortunately vfio-pci creates a map of config space, where ID 0 is used to reserve the standard type 0 header. Finding an actual capability with this ID therefore results in a bogus range marked in that map and conflicts with subsequent capabilities. As this seems to be a dummy capability anyway and we already support dropping capabilities, let's hide this one rather than delving into the potentially subtle dependencies within our map. Seen on an NVIDIA Tesla T4. Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- drivers/vfio/pci/vfio_pci_config.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index c2d300bc37f6..36bc8f104e42 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1464,7 +1464,12 @@ static int vfio_cap_init(struct vfio_pci_device *vdev) if (ret) return ret; - if (cap <= PCI_CAP_ID_MAX) { + /* + * ID 0 is a NULL capability, conflicting with our fake + * PCI_CAP_ID_BASIC. As it has no content, consider it + * hidden for now. + */ + if (cap && cap <= PCI_CAP_ID_MAX) { len = pci_cap_length[cap]; if (len == 0xFF) { /* Variable length */ len = vfio_cap_len(vdev, cap, pos); From baef809ea497a4f21fa67814b61094bbcc191c39 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 18 May 2020 16:49:29 +0100 Subject: [PATCH 082/162] usb/ohci-platform: Fix a warning when hibernating [ Upstream commit 1cb3b0095c3d0bb96912bfbbce4fc006d41f367c ] The following warning was observed when attempting to suspend to disk using a USB flash as a swap device. [ 111.779649] ------------[ cut here ]------------ [ 111.788382] URB (____ptrval____) submitted while active [ 111.796646] WARNING: CPU: 3 PID: 365 at drivers/usb/core/urb.c:363 usb_submit_urb+0x3d8/0x590 [ 111.805417] Modules linked in: [ 111.808584] CPU: 3 PID: 365 Comm: kworker/3:2 Not tainted 5.6.0-rc6-00002-gdfd1731f9a3e-dirty #545 [ 111.817796] Hardware name: ARM Juno development board (r2) (DT) [ 111.823896] Workqueue: usb_hub_wq hub_event [ 111.828217] pstate: 60000005 (nZCv daif -PAN -UAO) [ 111.833156] pc : usb_submit_urb+0x3d8/0x590 [ 111.837471] lr : usb_submit_urb+0x3d8/0x590 [ 111.841783] sp : ffff800018de38b0 [ 111.845205] x29: ffff800018de38b0 x28: 0000000000000003 [ 111.850682] x27: ffff000970530b20 x26: ffff8000133fd000 [ 111.856159] x25: ffff8000133fd000 x24: ffff800018de3b38 [ 111.861635] x23: 0000000000000004 x22: 0000000000000c00 [ 111.867112] x21: 0000000000000000 x20: 00000000fffffff0 [ 111.872589] x19: ffff0009704e7a00 x18: ffffffffffffffff [ 111.878065] x17: 00000000a7c8f4bc x16: 000000002af33de8 [ 111.883542] x15: ffff8000133fda88 x14: 0720072007200720 [ 111.889019] x13: 0720072007200720 x12: 0720072007200720 [ 111.894496] x11: 0000000000000000 x10: 00000000a5286134 [ 111.899973] x9 : 0000000000000002 x8 : ffff000970c837a0 [ 111.905449] x7 : 0000000000000000 x6 : ffff800018de3570 [ 111.910926] x5 : 0000000000000001 x4 : 0000000000000003 [ 111.916401] x3 : 0000000000000000 x2 : ffff800013427118 [ 111.921879] x1 : 9d4e965b4b7d7c00 x0 : 0000000000000000 [ 111.927356] Call trace: [ 111.929892] usb_submit_urb+0x3d8/0x590 [ 111.933852] hub_activate+0x108/0x7f0 [ 111.937633] hub_resume+0xac/0x148 [ 111.941149] usb_resume_interface.isra.10+0x60/0x138 [ 111.946265] usb_resume_both+0xe4/0x140 [ 111.950225] usb_runtime_resume+0x24/0x30 [ 111.954365] __rpm_callback+0xdc/0x138 [ 111.958236] rpm_callback+0x34/0x98 [ 111.961841] rpm_resume+0x4a8/0x720 [ 111.965445] rpm_resume+0x50c/0x720 [ 111.969049] __pm_runtime_resume+0x4c/0xb8 [ 111.973276] usb_autopm_get_interface+0x28/0x60 [ 111.977948] hub_event+0x80/0x16d8 [ 111.981466] process_one_work+0x2a4/0x748 [ 111.985604] worker_thread+0x48/0x498 [ 111.989387] kthread+0x13c/0x140 [ 111.992725] ret_from_fork+0x10/0x18 [ 111.996415] irq event stamp: 354 [ 111.999756] hardirqs last enabled at (353): [] console_unlock+0x504/0x5b8 [ 112.008441] hardirqs last disabled at (354): [] do_debug_exception+0x1a8/0x258 [ 112.017479] softirqs last enabled at (350): [] __do_softirq+0x4bc/0x568 [ 112.025984] softirqs last disabled at (343): [] irq_exit+0x144/0x150 [ 112.034129] ---[ end trace dc96030b9cf6c8a3 ]--- The problem was tracked down to a missing call to pm_runtime_set_active() on resume in ohci-platform. Link: https://lore.kernel.org/lkml/20200323143857.db5zphxhq4hz3hmd@e107158-lin.cambridge.arm.com/ Acked-by: Alan Stern Signed-off-by: Qais Yousef CC: Tony Prisk CC: Greg Kroah-Hartman CC: Mathias Nyman CC: Oliver Neukum CC: linux-arm-kernel@lists.infradead.org CC: linux-usb@vger.kernel.org CC: linux-kernel@vger.kernel.org Link: https://lore.kernel.org/r/20200518154931.6144-1-qais.yousef@arm.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/ohci-platform.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/host/ohci-platform.c b/drivers/usb/host/ohci-platform.c index 61fe2b985070..742cefa22c2b 100644 --- a/drivers/usb/host/ohci-platform.c +++ b/drivers/usb/host/ohci-platform.c @@ -355,6 +355,11 @@ static int ohci_platform_resume(struct device *dev) } ohci_resume(hcd, false); + + pm_runtime_disable(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + return 0; } #endif /* CONFIG_PM_SLEEP */ From 6838ddcd6713b081f91fb30cb42c852dea3b248c Mon Sep 17 00:00:00 2001 From: Roy Spliet Date: Tue, 7 Apr 2020 18:07:37 +0100 Subject: [PATCH 083/162] drm/msm/mdp5: Fix mdp5_init error path for failed mdp5_kms allocation [ Upstream commit e4337877c5d578722c0716f131fb774522013cf5 ] When allocation for mdp5_kms fails, calling mdp5_destroy() leads to undefined behaviour, likely a nullptr exception or use-after-free troubles. Signed-off-by: Roy Spliet Reviewed-by: Abhinav Kumar Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c index f7c0698fec40..791a74b9907d 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c @@ -972,7 +972,8 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev) return 0; fail: - mdp5_destroy(pdev); + if (mdp5_kms) + mdp5_destroy(pdev); return ret; } From 9bae486e00b76645bd95f1fa269225581391068b Mon Sep 17 00:00:00 2001 From: Tang Bin Date: Wed, 13 May 2020 21:26:47 +0800 Subject: [PATCH 084/162] USB: host: ehci-mxc: Add error handling in ehci_mxc_drv_probe() [ Upstream commit d49292025f79693d3348f8e2029a8b4703be0f0a ] The function ehci_mxc_drv_probe() does not perform sufficient error checking after executing platform_get_irq(), thus fix it. Fixes: 7e8d5cd93fac ("USB: Add EHCI support for MX27 and MX31 based boards") Signed-off-by: Zhang Shengju Signed-off-by: Tang Bin Reviewed-by: Peter Chen Link: https://lore.kernel.org/r/20200513132647.5456-1-tangbin@cmss.chinamobile.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/ehci-mxc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/host/ehci-mxc.c b/drivers/usb/host/ehci-mxc.c index c7a9b31eeaef..637079a35003 100644 --- a/drivers/usb/host/ehci-mxc.c +++ b/drivers/usb/host/ehci-mxc.c @@ -63,6 +63,8 @@ static int ehci_mxc_drv_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; hcd = usb_create_hcd(&ehci_mxc_hc_driver, dev, dev_name(dev)); if (!hcd) From 3fe2c3327ef42ffc7be5dedf706a3f4ec3b940b1 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Mon, 18 May 2020 10:45:13 +0200 Subject: [PATCH 085/162] tty: n_gsm: Fix bogus i++ in gsm_data_kick [ Upstream commit 4dd31f1ffec6c370c3c2e0c605628bf5e16d5c46 ] When submitting the previous fix "tty: n_gsm: Fix waking up upper tty layer when room available". It was suggested to switch from a while to a for loop, but when doing it, there was a remaining bogus i++. This patch removes this i++ and also reorganizes the code making it more compact. Fixes: e1eaea46bb40 ("tty: n_gsm line discipline") Signed-off-by: Gregory CLEMENT Link: https://lore.kernel.org/r/20200518084517.2173242-3-gregory.clement@bootlin.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/n_gsm.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index e7417eac3f21..c70e79a0e9f2 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -715,17 +715,9 @@ static void gsm_data_kick(struct gsm_mux *gsm, struct gsm_dlci *dlci) } else { int i = 0; - for (i = 0; i < NUM_DLCI; i++) { - struct gsm_dlci *dlci; - - dlci = gsm->dlci[i]; - if (dlci == NULL) { - i++; - continue; - } - - tty_port_tty_wakeup(&dlci->port); - } + for (i = 0; i < NUM_DLCI; i++) + if (gsm->dlci[i]) + tty_port_tty_wakeup(&gsm->dlci[i]->port); } } } From 8baeb6427c48a04e1edf8e0261e9627631846726 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 19 May 2020 12:26:52 +0200 Subject: [PATCH 086/162] clk: samsung: exynos5433: Add IGNORE_UNUSED flag to sclk_i2s1 [ Upstream commit 25bdae0f1c6609ceaf55fe6700654f0be2253d8e ] Mark the SCLK clock for Exynos5433 I2S1 device with IGNORE_UNUSED flag to match its behaviour with SCLK clock for AUD_I2S (I2S0) device until a proper fix for Exynos I2S driver is ready. This fixes the following synchronous abort issue revealed by the probe order change caused by the commit 93d2e4322aa7 ("of: platform: Batch fwnode parsing when adding all top level devices") Internal error: synchronous external abort: 96000210 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 50 Comm: kworker/0:1 Not tainted 5.7.0-rc5+ #701 Hardware name: Samsung TM2E board (DT) Workqueue: events deferred_probe_work_func pstate: 60000005 (nZCv daif -PAN -UAO) pc : samsung_i2s_probe+0x768/0x8f0 lr : samsung_i2s_probe+0x688/0x8f0 ... Call trace: samsung_i2s_probe+0x768/0x8f0 platform_drv_probe+0x50/0xa8 really_probe+0x108/0x370 driver_probe_device+0x54/0xb8 __device_attach_driver+0x90/0xc0 bus_for_each_drv+0x70/0xc8 __device_attach+0xdc/0x140 device_initial_probe+0x10/0x18 bus_probe_device+0x94/0xa0 deferred_probe_work_func+0x70/0xa8 process_one_work+0x2a8/0x718 worker_thread+0x48/0x470 kthread+0x134/0x160 ret_from_fork+0x10/0x1c Code: 17ffffaf d503201f f94086c0 91003000 (88dffc00) ---[ end trace ccf721c9400ddbd6 ]--- Signed-off-by: Marek Szyprowski Signed-off-by: Sylwester Nawrocki Signed-off-by: Sasha Levin --- drivers/clk/samsung/clk-exynos5433.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c index 1d2265f9ee97..1c327d5de98c 100644 --- a/drivers/clk/samsung/clk-exynos5433.c +++ b/drivers/clk/samsung/clk-exynos5433.c @@ -1674,7 +1674,8 @@ static const struct samsung_gate_clock peric_gate_clks[] __initconst = { GATE(CLK_SCLK_PCM1, "sclk_pcm1", "sclk_pcm1_peric", ENABLE_SCLK_PERIC, 7, CLK_SET_RATE_PARENT, 0), GATE(CLK_SCLK_I2S1, "sclk_i2s1", "sclk_i2s1_peric", - ENABLE_SCLK_PERIC, 6, CLK_SET_RATE_PARENT, 0), + ENABLE_SCLK_PERIC, 6, + CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED, 0), GATE(CLK_SCLK_SPI2, "sclk_spi2", "sclk_spi2_peric", ENABLE_SCLK_PERIC, 5, CLK_SET_RATE_PARENT, 0), GATE(CLK_SCLK_SPI1, "sclk_spi1", "sclk_spi1_peric", ENABLE_SCLK_PERIC, From 064b18b475a555c8e62fb96cbbecf8c0080ae689 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 5 Mar 2020 23:48:52 -0500 Subject: [PATCH 087/162] powerpc/64s/pgtable: fix an undefined behaviour [ Upstream commit c2e929b18cea6cbf71364f22d742d9aad7f4677a ] Booting a power9 server with hash MMU could trigger an undefined behaviour because pud_offset(p4d, 0) will do, 0 >> (PAGE_SHIFT:16 + PTE_INDEX_SIZE:8 + H_PMD_INDEX_SIZE:10) Fix it by converting pud_index() and friends to static inline functions. UBSAN: shift-out-of-bounds in arch/powerpc/mm/ptdump/ptdump.c:282:15 shift exponent 34 is too large for 32-bit type 'int' CPU: 6 PID: 1 Comm: swapper/0 Not tainted 5.6.0-rc4-next-20200303+ #13 Call Trace: dump_stack+0xf4/0x164 (unreliable) ubsan_epilogue+0x18/0x78 __ubsan_handle_shift_out_of_bounds+0x160/0x21c walk_pagetables+0x2cc/0x700 walk_pud at arch/powerpc/mm/ptdump/ptdump.c:282 (inlined by) walk_pagetables at arch/powerpc/mm/ptdump/ptdump.c:311 ptdump_check_wx+0x8c/0xf0 mark_rodata_ro+0x48/0x80 kernel_init+0x74/0x194 ret_from_kernel_thread+0x5c/0x74 Suggested-by: Christophe Leroy Signed-off-by: Qian Cai Signed-off-by: Michael Ellerman Reviewed-by: Christophe Leroy Link: https://lore.kernel.org/r/20200306044852.3236-1-cai@lca.pw Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/book3s/64/pgtable.h | 23 ++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index bcb79a96a6c8..618ee2c0ed53 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -898,10 +898,25 @@ extern struct page *pgd_page(pgd_t pgd); #define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) #define pgd_page_vaddr(pgd) __va(pgd_val(pgd) & ~PGD_MASKED_BITS) -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) -#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1)) -#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) -#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) +static inline unsigned long pgd_index(unsigned long address) +{ + return (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1); +} + +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} + +static inline unsigned long pmd_index(unsigned long address) +{ + return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); +} + +static inline unsigned long pte_index(unsigned long address) +{ + return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); +} /* * Find an entry in a page-table-directory. We combine the address region From 2296eda690db1c4619370d6c4f2624db6b3b3acd Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 19 May 2020 10:14:19 +0200 Subject: [PATCH 088/162] dm zoned: return NULL if dmz_get_zone_for_reclaim() fails to find a zone [ Upstream commit 489dc0f06a5837f87482c0ce61d830d24e17082e ] The only case where dmz_get_zone_for_reclaim() cannot return a zone is if the respective lists are empty. So we should just return a simple NULL value here as we really don't have an error code which would make sense. Signed-off-by: Hannes Reinecke Reviewed-by: Damien Le Moal Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-zoned-metadata.c | 4 ++-- drivers/md/dm-zoned-reclaim.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 4d658a0c6025..c6d3a4bc811c 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1580,7 +1580,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd) return dzone; } - return ERR_PTR(-EBUSY); + return NULL; } /* @@ -1600,7 +1600,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) return zone; } - return ERR_PTR(-EBUSY); + return NULL; } /* diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index 2fad512dce98..1015b200330b 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -350,8 +350,8 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) /* Get a data zone */ dzone = dmz_get_zone_for_reclaim(zmd); - if (IS_ERR(dzone)) - return PTR_ERR(dzone); + if (!dzone) + return -EBUSY; start = jiffies; From 6ccae103c95b44c7840b04ff73b6d3ef4c522fed Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 21 May 2020 15:40:07 -0500 Subject: [PATCH 089/162] PCI/PTM: Inherit Switch Downstream Port PTM settings from Upstream Port [ Upstream commit 7b38fd9760f51cc83d80eed2cfbde8b5ead9e93a ] Except for Endpoints, we enable PTM at enumeration-time. Previously we did not account for the fact that Switch Downstream Ports are not permitted to have a PTM capability; their PTM behavior is controlled by the Upstream Port (PCIe r5.0, sec 7.9.16). Since Downstream Ports don't have a PTM capability, we did not mark them as "ptm_enabled", which meant that pci_enable_ptm() on an Endpoint failed because there was no PTM path to it. Mark Downstream Ports as "ptm_enabled" if their Upstream Port has PTM enabled. Fixes: eec097d43100 ("PCI: Add pci_enable_ptm() for drivers to enable PTM on endpoints") Reported-by: Aditya Paluri Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/pcie/ptm.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 3008bba360f3..ec6f6213960b 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -47,10 +47,6 @@ void pci_ptm_init(struct pci_dev *dev) if (!pci_is_pcie(dev)) return; - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM); - if (!pos) - return; - /* * Enable PTM only on interior devices (root ports, switch ports, * etc.) on the assumption that it causes no link traffic until an @@ -60,6 +56,23 @@ void pci_ptm_init(struct pci_dev *dev) pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END)) return; + /* + * Switch Downstream Ports are not permitted to have a PTM + * capability; their PTM behavior is controlled by the Upstream + * Port (PCIe r5.0, sec 7.9.16). + */ + ups = pci_upstream_bridge(dev); + if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM && + ups && ups->ptm_enabled) { + dev->ptm_granularity = ups->ptm_granularity; + dev->ptm_enabled = 1; + return; + } + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM); + if (!pos) + return; + pci_read_config_dword(dev, pos + PCI_PTM_CAP, &cap); local_clock = (cap & PCI_PTM_GRANULARITY_MASK) >> 8; @@ -69,7 +82,6 @@ void pci_ptm_init(struct pci_dev *dev) * the spec recommendation (PCIe r3.1, sec 7.32.3), select the * furthest upstream Time Source as the PTM Root. */ - ups = pci_upstream_bridge(dev); if (ups && ups->ptm_enabled) { ctrl = PCI_PTM_CTRL_ENABLE; if (ups->ptm_granularity == 0) From 7ee2a9dee4c00cfa5290ac8e1939adbc7979f528 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 21 May 2020 10:26:50 +0300 Subject: [PATCH 090/162] IB/cma: Fix ports memory leak in cma_configfs [ Upstream commit 63a3345c2d42a9b29e1ce2d3a4043689b3995cea ] The allocated ports structure in never freed. The free function should be called by release_cma_ports_group, but the group is never released since we don't remove its default group. Remove default groups when device group is deleted. Fixes: 045959db65c6 ("IB/cma: Add configfs for rdma_cm") Link: https://lore.kernel.org/r/20200521072650.567908-1-leon@kernel.org Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/core/cma_configfs.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c index 54076a3e8007..ac47e8a1dfbf 100644 --- a/drivers/infiniband/core/cma_configfs.c +++ b/drivers/infiniband/core/cma_configfs.c @@ -319,8 +319,21 @@ fail: return ERR_PTR(err); } +static void drop_cma_dev(struct config_group *cgroup, struct config_item *item) +{ + struct config_group *group = + container_of(item, struct config_group, cg_item); + struct cma_dev_group *cma_dev_group = + container_of(group, struct cma_dev_group, device_group); + + configfs_remove_default_groups(&cma_dev_group->ports_group); + configfs_remove_default_groups(&cma_dev_group->device_group); + config_item_put(item); +} + static struct configfs_group_operations cma_subsys_group_ops = { .make_group = make_cma_dev, + .drop_item = drop_cma_dev, }; static struct config_item_type cma_subsys_type = { From d704910430ea95788334375a4b91db9d178b8c12 Mon Sep 17 00:00:00 2001 From: Stefan Riedmueller Date: Fri, 3 Apr 2020 15:07:28 +0200 Subject: [PATCH 091/162] watchdog: da9062: No need to ping manually before setting timeout [ Upstream commit a0948ddba65f4f6d3cfb5e2b84685485d0452966 ] There is actually no need to ping the watchdog before disabling it during timeout change. Disabling the watchdog already takes care of resetting the counter. This fixes an issue during boot when the userspace watchdog handler takes over and the watchdog is already running. Opening the watchdog in this case leads to the first ping and directly after that without the required heartbeat delay a second ping issued by the set_timeout call. Due to the missing delay this resulted in a reset. Signed-off-by: Stefan Riedmueller Reviewed-by: Guenter Roeck Reviewed-by: Adam Thomson Link: https://lore.kernel.org/r/20200403130728.39260-3-s.riedmueller@phytec.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/da9062_wdt.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c index 79383ff62019..1443386bb590 100644 --- a/drivers/watchdog/da9062_wdt.c +++ b/drivers/watchdog/da9062_wdt.c @@ -94,11 +94,6 @@ static int da9062_wdt_update_timeout_register(struct da9062_watchdog *wdt, unsigned int regval) { struct da9062 *chip = wdt->hw; - int ret; - - ret = da9062_reset_watchdog_timer(wdt); - if (ret) - return ret; return regmap_update_bits(chip->regmap, DA9062AA_CONTROL_D, From 5c6d306dffe5a65c3ec1ce66549261304dcdf83f Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Thu, 23 Apr 2020 13:55:53 +0200 Subject: [PATCH 092/162] usb: dwc2: gadget: move gadget resume after the core is in L0 state [ Upstream commit 8c935deacebb8fac8f41378701eb79d12f3c2e2d ] When the remote wakeup interrupt is triggered, lx_state is resumed from L2 to L0 state. But when the gadget resume is called, lx_state is still L2. This prevents the resume callback to queue any request. Any attempt to queue a request from resume callback will result in: - "submit request only in active state" debug message to be issued - dwc2_hsotg_ep_queue() returns -EAGAIN Call the gadget resume routine after the core is in L0 state. Fixes: f81f46e1f530 ("usb: dwc2: implement hibernation during bus suspend/resume") Acked-by: Minas Harutyunyan Signed-off-by: Fabrice Gasnier Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/dwc2/core_intr.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index b8bcb007c92a..e3e0a3ab31da 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -364,10 +364,13 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) if (ret && (ret != -ENOTSUPP)) dev_err(hsotg->dev, "exit hibernation failed\n"); + /* Change to L0 state */ + hsotg->lx_state = DWC2_L0; call_gadget(hsotg, resume); + } else { + /* Change to L0 state */ + hsotg->lx_state = DWC2_L0; } - /* Change to L0 state */ - hsotg->lx_state = DWC2_L0; } else { if (hsotg->params.hibernation) return; From 59626dc2cae4e38cf2bf34981cfdea5606925daa Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 23 Apr 2020 09:29:24 -0700 Subject: [PATCH 093/162] USB: gadget: udc: s3c2410_udc: Remove pointless NULL check in s3c2410_udc_nuke [ Upstream commit 7a0fbcf7c308920bc6116b3a5fb21c8cc5fec128 ] Clang warns: drivers/usb/gadget/udc/s3c2410_udc.c:255:11: warning: comparison of address of 'ep->queue' equal to a null pointer is always false [-Wtautological-pointer-compare] if (&ep->queue == NULL) ~~~~^~~~~ ~~~~ 1 warning generated. It is not wrong, queue is not a pointer so if ep is not NULL, the address of queue cannot be NULL. No other driver does a check like this and this check has been around since the driver was first introduced, presumably with no issues so it does not seem like this check should be something else. Just remove it. Commit afe956c577b2d ("kbuild: Enable -Wtautological-compare") exposed this but it is not the root cause of the warning. Fixes: 3fc154b6b8134 ("USB Gadget driver for Samsung s3c2410 ARM SoC") Link: https://github.com/ClangBuiltLinux/linux/issues/1004 Reviewed-by: Nick Desaulniers Reported-by: kbuild test robot Signed-off-by: Nathan Chancellor Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/s3c2410_udc.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/usb/gadget/udc/s3c2410_udc.c b/drivers/usb/gadget/udc/s3c2410_udc.c index 394abd5d65c0..cf12ca567e69 100644 --- a/drivers/usb/gadget/udc/s3c2410_udc.c +++ b/drivers/usb/gadget/udc/s3c2410_udc.c @@ -268,10 +268,6 @@ static void s3c2410_udc_done(struct s3c2410_ep *ep, static void s3c2410_udc_nuke(struct s3c2410_udc *udc, struct s3c2410_ep *ep, int status) { - /* Sanity check */ - if (&ep->queue == NULL) - return; - while (!list_empty(&ep->queue)) { struct s3c2410_request *req; req = list_entry(ep->queue.next, struct s3c2410_request, From dcbdb5f08ec74750ba791dd4801e09c5fb6596bb Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 21 May 2020 16:13:00 +0100 Subject: [PATCH 094/162] usb: gadget: lpc32xx_udc: don't dereference ep pointer before null check [ Upstream commit eafa80041645cd7604c4357b1a0cd4a3c81f2227 ] Currently pointer ep is being dereferenced before it is null checked leading to a null pointer dereference issue. Fix this by only assigning pointer udc once ep is known to be not null. Also remove a debug message that requires a valid udc which may not be possible at that point. Addresses-Coverity: ("Dereference before null check") Fixes: 24a28e428351 ("USB: gadget driver for LPC32xx") Signed-off-by: Colin Ian King Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/lpc32xx_udc.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c index ac2aa04ca657..710793161795 100644 --- a/drivers/usb/gadget/udc/lpc32xx_udc.c +++ b/drivers/usb/gadget/udc/lpc32xx_udc.c @@ -1615,17 +1615,17 @@ static int lpc32xx_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc) { struct lpc32xx_ep *ep = container_of(_ep, struct lpc32xx_ep, ep); - struct lpc32xx_udc *udc = ep->udc; + struct lpc32xx_udc *udc; u16 maxpacket; u32 tmp; unsigned long flags; /* Verify EP data */ if ((!_ep) || (!ep) || (!desc) || - (desc->bDescriptorType != USB_DT_ENDPOINT)) { - dev_dbg(udc->dev, "bad ep or descriptor\n"); + (desc->bDescriptorType != USB_DT_ENDPOINT)) return -EINVAL; - } + + udc = ep->udc; maxpacket = usb_endpoint_maxp(desc); if ((maxpacket == 0) || (maxpacket > ep->maxpacket)) { dev_dbg(udc->dev, "bad ep descriptor's packet size\n"); @@ -1873,7 +1873,7 @@ static int lpc32xx_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req) static int lpc32xx_ep_set_halt(struct usb_ep *_ep, int value) { struct lpc32xx_ep *ep = container_of(_ep, struct lpc32xx_ep, ep); - struct lpc32xx_udc *udc = ep->udc; + struct lpc32xx_udc *udc; unsigned long flags; if ((!ep) || (ep->hwep_num <= 1)) @@ -1883,6 +1883,7 @@ static int lpc32xx_ep_set_halt(struct usb_ep *_ep, int value) if (ep->is_in) return -EAGAIN; + udc = ep->udc; spin_lock_irqsave(&udc->lock, flags); if (value == 1) { From 264175bd94374683d4b0f4944294b44878defe87 Mon Sep 17 00:00:00 2001 From: Qiushi Wu Date: Fri, 22 May 2020 23:06:25 -0500 Subject: [PATCH 095/162] usb: gadget: fix potential double-free in m66592_probe. [ Upstream commit 44734a594196bf1d474212f38fe3a0d37a73278b ] m66592_free_request() is called under label "err_add_udc" and "clean_up", and m66592->ep0_req is not set to NULL after first free, leading to a double-free. Fix this issue by setting m66592->ep0_req to NULL after the first free. Fixes: 0f91349b89f3 ("usb: gadget: convert all users to the new udc infrastructure") Signed-off-by: Qiushi Wu Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/m66592-udc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/m66592-udc.c b/drivers/usb/gadget/udc/m66592-udc.c index 46ce7bc15f2b..53abad98af6d 100644 --- a/drivers/usb/gadget/udc/m66592-udc.c +++ b/drivers/usb/gadget/udc/m66592-udc.c @@ -1672,7 +1672,7 @@ static int m66592_probe(struct platform_device *pdev) err_add_udc: m66592_free_request(&m66592->ep[0].ep, m66592->ep0_req); - + m66592->ep0_req = NULL; clean_up3: if (m66592->pdata->on_chip) { clk_disable(m66592->clk); From 0c8c366c54f07f70d03260db9e0faa52f8d65749 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Mon, 18 May 2020 12:08:45 +0200 Subject: [PATCH 096/162] usb: gadget: Fix issue with config_ep_by_speed function [ Upstream commit 5d363120aa548ba52d58907a295eee25f8207ed2 ] This patch adds new config_ep_by_speed_and_alt function which extends the config_ep_by_speed about alt parameter. This additional parameter allows to find proper usb_ss_ep_comp_descriptor. Problem has appeared during testing f_tcm (BOT/UAS) driver function. f_tcm function for SS use array of headers for both BOT/UAS alternate setting: static struct usb_descriptor_header *uasp_ss_function_desc[] = { (struct usb_descriptor_header *) &bot_intf_desc, (struct usb_descriptor_header *) &uasp_ss_bi_desc, (struct usb_descriptor_header *) &bot_bi_ep_comp_desc, (struct usb_descriptor_header *) &uasp_ss_bo_desc, (struct usb_descriptor_header *) &bot_bo_ep_comp_desc, (struct usb_descriptor_header *) &uasp_intf_desc, (struct usb_descriptor_header *) &uasp_ss_bi_desc, (struct usb_descriptor_header *) &uasp_bi_ep_comp_desc, (struct usb_descriptor_header *) &uasp_bi_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_bo_desc, (struct usb_descriptor_header *) &uasp_bo_ep_comp_desc, (struct usb_descriptor_header *) &uasp_bo_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_status_desc, (struct usb_descriptor_header *) &uasp_status_in_ep_comp_desc, (struct usb_descriptor_header *) &uasp_status_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_cmd_desc, (struct usb_descriptor_header *) &uasp_cmd_comp_desc, (struct usb_descriptor_header *) &uasp_cmd_pipe_desc, NULL, }; The first 5 descriptors are associated with BOT alternate setting, and others are associated with UAS. During handling UAS alternate setting f_tcm driver invokes config_ep_by_speed and this function sets incorrect companion endpoint descriptor in usb_ep object. Instead setting ep->comp_desc to uasp_bi_ep_comp_desc function in this case set ep->comp_desc to uasp_ss_bi_desc. This is due to the fact that it searches endpoint based on endpoint address: for_each_ep_desc(speed_desc, d_spd) { chosen_desc = (struct usb_endpoint_descriptor *)*d_spd; if (chosen_desc->bEndpoitAddress == _ep->address) goto ep_found; } And in result it uses the descriptor from BOT alternate setting instead UAS. Finally, it causes that controller driver during enabling endpoints detect that just enabled endpoint for bot. Signed-off-by: Jayshri Pawar Signed-off-by: Pawel Laszczak Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/composite.c | 78 ++++++++++++++++++++++++++-------- include/linux/usb/composite.h | 3 ++ 2 files changed, 64 insertions(+), 17 deletions(-) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index c1f037af9702..7d2715e899bb 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -100,40 +100,43 @@ function_descriptors(struct usb_function *f, } /** - * next_ep_desc() - advance to the next EP descriptor + * next_desc() - advance to the next desc_type descriptor * @t: currect pointer within descriptor array + * @desc_type: descriptor type * - * Return: next EP descriptor or NULL + * Return: next desc_type descriptor or NULL * - * Iterate over @t until either EP descriptor found or + * Iterate over @t until either desc_type descriptor found or * NULL (that indicates end of list) encountered */ static struct usb_descriptor_header** -next_ep_desc(struct usb_descriptor_header **t) +next_desc(struct usb_descriptor_header **t, u8 desc_type) { for (; *t; t++) { - if ((*t)->bDescriptorType == USB_DT_ENDPOINT) + if ((*t)->bDescriptorType == desc_type) return t; } return NULL; } /* - * for_each_ep_desc()- iterate over endpoint descriptors in the - * descriptors list - * @start: pointer within descriptor array. - * @ep_desc: endpoint descriptor to use as the loop cursor + * for_each_desc() - iterate over desc_type descriptors in the + * descriptors list + * @start: pointer within descriptor array. + * @iter_desc: desc_type descriptor to use as the loop cursor + * @desc_type: wanted descriptr type */ -#define for_each_ep_desc(start, ep_desc) \ - for (ep_desc = next_ep_desc(start); \ - ep_desc; ep_desc = next_ep_desc(ep_desc+1)) +#define for_each_desc(start, iter_desc, desc_type) \ + for (iter_desc = next_desc(start, desc_type); \ + iter_desc; iter_desc = next_desc(iter_desc + 1, desc_type)) /** - * config_ep_by_speed() - configures the given endpoint + * config_ep_by_speed_and_alt() - configures the given endpoint * according to gadget speed. * @g: pointer to the gadget * @f: usb function * @_ep: the endpoint to configure + * @alt: alternate setting number * * Return: error code, 0 on success * @@ -146,11 +149,13 @@ next_ep_desc(struct usb_descriptor_header **t) * Note: the supplied function should hold all the descriptors * for supported speeds */ -int config_ep_by_speed(struct usb_gadget *g, - struct usb_function *f, - struct usb_ep *_ep) +int config_ep_by_speed_and_alt(struct usb_gadget *g, + struct usb_function *f, + struct usb_ep *_ep, + u8 alt) { struct usb_endpoint_descriptor *chosen_desc = NULL; + struct usb_interface_descriptor *int_desc = NULL; struct usb_descriptor_header **speed_desc = NULL; struct usb_ss_ep_comp_descriptor *comp_desc = NULL; @@ -186,8 +191,21 @@ int config_ep_by_speed(struct usb_gadget *g, default: speed_desc = f->fs_descriptors; } + + /* find correct alternate setting descriptor */ + for_each_desc(speed_desc, d_spd, USB_DT_INTERFACE) { + int_desc = (struct usb_interface_descriptor *)*d_spd; + + if (int_desc->bAlternateSetting == alt) { + speed_desc = d_spd; + goto intf_found; + } + } + return -EIO; + +intf_found: /* find descriptors */ - for_each_ep_desc(speed_desc, d_spd) { + for_each_desc(speed_desc, d_spd, USB_DT_ENDPOINT) { chosen_desc = (struct usb_endpoint_descriptor *)*d_spd; if (chosen_desc->bEndpointAddress == _ep->address) goto ep_found; @@ -240,6 +258,32 @@ ep_found: } return 0; } +EXPORT_SYMBOL_GPL(config_ep_by_speed_and_alt); + +/** + * config_ep_by_speed() - configures the given endpoint + * according to gadget speed. + * @g: pointer to the gadget + * @f: usb function + * @_ep: the endpoint to configure + * + * Return: error code, 0 on success + * + * This function chooses the right descriptors for a given + * endpoint according to gadget speed and saves it in the + * endpoint desc field. If the endpoint already has a descriptor + * assigned to it - overwrites it with currently corresponding + * descriptor. The endpoint maxpacket field is updated according + * to the chosen descriptor. + * Note: the supplied function should hold all the descriptors + * for supported speeds + */ +int config_ep_by_speed(struct usb_gadget *g, + struct usb_function *f, + struct usb_ep *_ep) +{ + return config_ep_by_speed_and_alt(g, f, _ep, 0); +} EXPORT_SYMBOL_GPL(config_ep_by_speed); /** diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 590d313b5f39..a865698361c1 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -248,6 +248,9 @@ int usb_function_activate(struct usb_function *); int usb_interface_id(struct usb_configuration *, struct usb_function *); +int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f, + struct usb_ep *_ep, u8 alt); + int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); From 3f5e5a0553918c9200b55b19180b0e4089406e4d Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 25 May 2020 12:38:39 +0200 Subject: [PATCH 097/162] x86/apic: Make TSC deadline timer detection message visible [ Upstream commit de308d1815c9e8fe602a958c5c76142ff6501d75 ] The commit c84cb3735fd5 ("x86/apic: Move TSC deadline timer debug printk") removed the message which said that the deadline timer was enabled. It added a pr_debug() message which is issued when deadline timer validation succeeds. Well, issued only when CONFIG_DYNAMIC_DEBUG is enabled - otherwise pr_debug() calls get optimized away if DEBUG is not defined in the compilation unit. Therefore, make the above message pr_info() so that it is visible in dmesg. Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200525104218.27018-1-bp@alien8.de Signed-off-by: Sasha Levin --- arch/x86/kernel/apic/apic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 48ab5fdd1044..ee33f0951322 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1915,7 +1915,7 @@ void __init init_apic_mappings(void) unsigned int new_apicid; if (apic_validate_deadline_timer()) - pr_debug("TSC deadline timer available\n"); + pr_info("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); From b4671b5ca22ec0e81a6fcc30f4a50b0dd78740d5 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Sat, 16 May 2020 01:08:06 -0700 Subject: [PATCH 098/162] clk: bcm2835: Fix return type of bcm2835_register_gate [ Upstream commit f376c43bec4f8ee8d1ba5c5c4cfbd6e84fb279cb ] bcm2835_register_gate is used as a callback for the clk_register member of bcm2835_clk_desc, which expects a struct clk_hw * return type but bcm2835_register_gate returns a struct clk *. This discrepancy is hidden by the fact that bcm2835_register_gate is cast to the typedef bcm2835_clk_register by the _REGISTER macro. This turns out to be a control flow integrity violation, which is how this was noticed. Change the return type of bcm2835_register_gate to be struct clk_hw * and use clk_hw_register_gate to do so. This should be a non-functional change as clk_register_gate calls clk_hw_register_gate anyways but this is needed to avoid issues with further changes. Fixes: b19f009d4510 ("clk: bcm2835: Migrate to clk_hw based registration and OF APIs") Link: https://github.com/ClangBuiltLinux/linux/issues/1028 Signed-off-by: Nathan Chancellor Link: https://lkml.kernel.org/r/20200516080806.1459784-1-natechancellor@gmail.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/bcm/clk-bcm2835.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 5f8082d89131..6db4204e5d5d 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -1483,13 +1483,13 @@ static struct clk_hw *bcm2835_register_clock(struct bcm2835_cprman *cprman, return &clock->hw; } -static struct clk *bcm2835_register_gate(struct bcm2835_cprman *cprman, +static struct clk_hw *bcm2835_register_gate(struct bcm2835_cprman *cprman, const struct bcm2835_gate_data *data) { - return clk_register_gate(cprman->dev, data->name, data->parent, - CLK_IGNORE_UNUSED | CLK_SET_RATE_GATE, - cprman->regs + data->ctl_reg, - CM_GATE_BIT, 0, &cprman->regs_lock); + return clk_hw_register_gate(cprman->dev, data->name, data->parent, + CLK_IGNORE_UNUSED | CLK_SET_RATE_GATE, + cprman->regs + data->ctl_reg, + CM_GATE_BIT, 0, &cprman->regs_lock); } typedef struct clk_hw *(*bcm2835_clk_register)(struct bcm2835_cprman *cprman, From 291ae253fb695258fbdf2d73f5f37b43f597e537 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 25 May 2020 13:41:25 -0700 Subject: [PATCH 099/162] scsi: ufs-qcom: Fix scheduling while atomic issue [ Upstream commit 3be60b564de49875e47974c37fabced893cd0931 ] ufs_qcom_dump_dbg_regs() uses usleep_range, a sleeping function, but can be called from atomic context in the following flow: ufshcd_intr -> ufshcd_sl_intr -> ufshcd_check_errors -> ufshcd_print_host_regs -> ufshcd_vops_dbg_register_dump -> ufs_qcom_dump_dbg_regs This causes a boot crash on the Lenovo Miix 630 when the interrupt is handled on the idle thread. Fix the issue by switching to udelay(). Link: https://lore.kernel.org/r/20200525204125.46171-1-jeffrey.l.hugo@gmail.com Fixes: 9c46b8676271 ("scsi: ufs-qcom: dump additional testbus registers") Reviewed-by: Bean Huo Reviewed-by: Avri Altman Signed-off-by: Jeffrey Hugo Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ufs/ufs-qcom.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index f2b8de195d8a..ee3589ac64ab 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -1649,11 +1649,11 @@ static void ufs_qcom_dump_dbg_regs(struct ufs_hba *hba) /* sleep a bit intermittently as we are dumping too much data */ ufs_qcom_print_hw_debug_reg_all(hba, NULL, ufs_qcom_dump_regs_wrapper); - usleep_range(1000, 1100); + udelay(1000); ufs_qcom_testbus_read(hba); - usleep_range(1000, 1100); + udelay(1000); ufs_qcom_print_unipro_testbus(hba); - usleep_range(1000, 1100); + udelay(1000); } /** From e6693998949c90c6c602da0906d381303142d9fc Mon Sep 17 00:00:00 2001 From: Fedor Tokarev Date: Sat, 28 Mar 2020 14:56:55 +0300 Subject: [PATCH 100/162] net: sunrpc: Fix off-by-one issues in 'rpc_ntop6' [ Upstream commit 118917d696dc59fd3e1741012c2f9db2294bed6f ] Fix off-by-one issues in 'rpc_ntop6': - 'snprintf' returns the number of characters which would have been written if enough space had been available, excluding the terminating null byte. Thus, a return value of 'sizeof(scopebuf)' means that the last character was dropped. - 'strcat' adds a terminating null byte to the string, thus if len == buflen, the null byte is written past the end of the buffer. Signed-off-by: Fedor Tokarev Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- net/sunrpc/addr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index 2e0a6f92e563..8391c2785550 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -81,11 +81,11 @@ static size_t rpc_ntop6(const struct sockaddr *sap, rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u", IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id); - if (unlikely((size_t)rc > sizeof(scopebuf))) + if (unlikely((size_t)rc >= sizeof(scopebuf))) return 0; len += rc; - if (unlikely(len > buflen)) + if (unlikely(len >= buflen)) return 0; strcat(buf, scopebuf); From c5f234ce6768356ffd2064c09476a04b0266669b Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Sun, 26 Apr 2020 11:30:00 -0400 Subject: [PATCH 101/162] NFSv4.1 fix rpc_call_done assignment for BIND_CONN_TO_SESSION [ Upstream commit 1c709b766e73e54d64b1dde1b7cfbcf25bcb15b9 ] Fixes: 02a95dee8cf0 ("NFS add callback_ops to nfs4_proc_bind_conn_to_session_callback") Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4d45786738ab..a19bbcfab7c5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7309,7 +7309,7 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) } static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = { - .rpc_call_done = &nfs4_bind_one_conn_to_session_done, + .rpc_call_done = nfs4_bind_one_conn_to_session_done, }; /* From ba112d00f50c32682485c6e67904ca5a17c36373 Mon Sep 17 00:00:00 2001 From: huhai Date: Thu, 21 May 2020 17:26:48 +1000 Subject: [PATCH 102/162] powerpc/4xx: Don't unmap NULL mbase [ Upstream commit bcec081ecc940fc38730b29c743bbee661164161 ] Signed-off-by: huhai Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200521072648.1254699-1-mpe@ellerman.id.au Signed-off-by: Sasha Levin --- arch/powerpc/platforms/4xx/pci.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c index 73e6b36bcd51..256943af58aa 100644 --- a/arch/powerpc/platforms/4xx/pci.c +++ b/arch/powerpc/platforms/4xx/pci.c @@ -1242,7 +1242,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) if (mbase == NULL) { printk(KERN_ERR "%pOF: Can't map internal config space !", port->node); - goto done; + return; } while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA) @@ -1252,9 +1252,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) } if (attempt) port->link = 1; -done: iounmap(mbase); - } static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = { From c8c6ce040bf588541324afd2024c1a37c84033cf Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 10 May 2020 11:53:03 +0200 Subject: [PATCH 103/162] extcon: adc-jack: Fix an error handling path in 'adc_jack_probe()' [ Upstream commit bc84cff2c92ae5ccb2c37da73756e7174b1b430f ] In some error handling paths, a call to 'iio_channel_get()' is not balanced by a corresponding call to 'iio_channel_release()'. This can be achieved easily by using the devm_ variant of 'iio_channel_get()'. This has the extra benefit to simplify the remove function. Fixes: 19939860dcae ("extcon: adc_jack: adc-jack driver to support 3.5 pi or simliar devices") Signed-off-by: Christophe JAILLET Signed-off-by: Chanwoo Choi Signed-off-by: Sasha Levin --- drivers/extcon/extcon-adc-jack.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c index 6f6537ab0a79..59e6ca685be8 100644 --- a/drivers/extcon/extcon-adc-jack.c +++ b/drivers/extcon/extcon-adc-jack.c @@ -128,7 +128,7 @@ static int adc_jack_probe(struct platform_device *pdev) for (i = 0; data->adc_conditions[i].id != EXTCON_NONE; i++); data->num_conditions = i; - data->chan = iio_channel_get(&pdev->dev, pdata->consumer_channel); + data->chan = devm_iio_channel_get(&pdev->dev, pdata->consumer_channel); if (IS_ERR(data->chan)) return PTR_ERR(data->chan); @@ -170,7 +170,6 @@ static int adc_jack_remove(struct platform_device *pdev) free_irq(data->irq, data); cancel_work_sync(&data->handler.work); - iio_channel_release(data->chan); return 0; } From f4691f8329ff95f588d06619627f9c84972a0f1f Mon Sep 17 00:00:00 2001 From: Xiyu Yang Date: Mon, 25 May 2020 22:12:46 +0800 Subject: [PATCH 104/162] ASoC: fsl_asrc_dma: Fix dma_chan leak when config DMA channel failed [ Upstream commit 36124fb19f1ae68a500cd76a76d40c6e81bee346 ] fsl_asrc_dma_hw_params() invokes dma_request_channel() or fsl_asrc_get_dma_channel(), which returns a reference of the specified dma_chan object to "pair->dma_chan[dir]" with increased refcnt. The reference counting issue happens in one exception handling path of fsl_asrc_dma_hw_params(). When config DMA channel failed for Back-End, the function forgets to decrease the refcnt increased by dma_request_channel() or fsl_asrc_get_dma_channel(), causing a refcnt leak. Fix this issue by calling dma_release_channel() when config DMA channel failed. Signed-off-by: Xiyu Yang Signed-off-by: Xin Tan Link: https://lore.kernel.org/r/1590415966-52416-1-git-send-email-xiyuyang19@fudan.edu.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_asrc_dma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c index e1b97e59275a..15d7e6da0555 100644 --- a/sound/soc/fsl/fsl_asrc_dma.c +++ b/sound/soc/fsl/fsl_asrc_dma.c @@ -243,6 +243,7 @@ static int fsl_asrc_dma_hw_params(struct snd_pcm_substream *substream, ret = dmaengine_slave_config(pair->dma_chan[dir], &config_be); if (ret) { dev_err(dev, "failed to config DMA channel for Back-End\n"); + dma_release_channel(pair->dma_chan[dir]); return ret; } From fcc43e9661344ac99aef9fac18ff850fd9cc8894 Mon Sep 17 00:00:00 2001 From: Qiushi Wu Date: Wed, 27 May 2020 21:01:09 -0500 Subject: [PATCH 105/162] vfio/mdev: Fix reference count leak in add_mdev_supported_type [ Upstream commit aa8ba13cae3134b8ef1c1b6879f66372531da738 ] kobject_init_and_add() takes reference even when it fails. If this function returns an error, kobject_put() must be called to properly clean up the memory associated with the object. Thus, replace kfree() by kobject_put() to fix this issue. Previous commit "b8eb718348b8" fixed a similar problem. Fixes: 7b96953bc640 ("vfio: Mediated device Core driver") Signed-off-by: Qiushi Wu Reviewed-by: Cornelia Huck Reviewed-by: Kirti Wankhede Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- drivers/vfio/mdev/mdev_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c index 802df210929b..7e474e41c85e 100644 --- a/drivers/vfio/mdev/mdev_sysfs.c +++ b/drivers/vfio/mdev/mdev_sysfs.c @@ -113,7 +113,7 @@ struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent, "%s-%s", dev_driver_string(parent->dev), group->name); if (ret) { - kfree(type); + kobject_put(&type->kobj); return ERR_PTR(ret); } From ea9b94947d0f03f6042e22b25578c0e18f189a03 Mon Sep 17 00:00:00 2001 From: Stafford Horne Date: Wed, 22 Apr 2020 20:24:11 +0900 Subject: [PATCH 106/162] openrisc: Fix issue with argument clobbering for clone/fork [ Upstream commit 6bd140e14d9aaa734ec37985b8b20a96c0ece948 ] Working on the OpenRISC glibc port I found that sometimes clone was working strange. That the tls data argument sent in r7 was always wrong. Further investigation revealed that the arguments were getting clobbered in the entry code. This patch removes the code that writes to the argument registers. This was likely due to some old code hanging around. This patch fixes this up for clone and fork. This fork clobber is harmless but also useless so remove. Signed-off-by: Stafford Horne Signed-off-by: Sasha Levin --- arch/openrisc/kernel/entry.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index 1107d34e45bf..0fdfa7142f4b 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -1102,13 +1102,13 @@ ENTRY(__sys_clone) l.movhi r29,hi(sys_clone) l.ori r29,r29,lo(sys_clone) l.j _fork_save_extra_regs_and_call - l.addi r7,r1,0 + l.nop ENTRY(__sys_fork) l.movhi r29,hi(sys_fork) l.ori r29,r29,lo(sys_fork) l.j _fork_save_extra_regs_and_call - l.addi r3,r1,0 + l.nop ENTRY(sys_rt_sigreturn) l.jal _sys_rt_sigreturn From 5bd3a2e81a1e48127841e4fa91472503ec517464 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Wed, 29 Apr 2020 08:45:54 -0500 Subject: [PATCH 107/162] gfs2: Allow lock_nolock mount to specify jid=X [ Upstream commit ea22eee4e6027d8927099de344f7fff43c507ef9 ] Before this patch, a simple typo accidentally added \n to the jid= string for lock_nolock mounts. This made it impossible to mount a gfs2 file system with a journal other than journal0. Thus: mount -tgfs2 -o hostdata="jid=1" Resulted in: mount: wrong fs type, bad option, bad superblock on In most cases this is not a problem. However, for debugging and testing purposes we sometimes want to test the integrity of other journals. This patch removes the unnecessary \n and thus allows lock_nolock users to specify an alternate journal. Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/ops_fstype.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 057be88eb1b4..7ed0359ebac6 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -922,7 +922,7 @@ fail: } static const match_table_t nolock_tokens = { - { Opt_jid, "jid=%d\n", }, + { Opt_jid, "jid=%d", }, { Opt_err, NULL }, }; From 0bda10eb793c8de7d3ec78f9cf2a332a3981f387 Mon Sep 17 00:00:00 2001 From: Qiushi Wu Date: Thu, 28 May 2020 15:13:53 -0500 Subject: [PATCH 108/162] scsi: iscsi: Fix reference count leak in iscsi_boot_create_kobj [ Upstream commit 0267ffce562c8bbf9b57ebe0e38445ad04972890 ] kobject_init_and_add() takes reference even when it fails. If this function returns an error, kobject_put() must be called to properly clean up the memory associated with the object. Link: https://lore.kernel.org/r/20200528201353.14849-1-wu000273@umn.edu Reviewed-by: Lee Duncan Signed-off-by: Qiushi Wu Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/iscsi_boot_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/iscsi_boot_sysfs.c b/drivers/scsi/iscsi_boot_sysfs.c index d453667612f8..15d64f96e623 100644 --- a/drivers/scsi/iscsi_boot_sysfs.c +++ b/drivers/scsi/iscsi_boot_sysfs.c @@ -360,7 +360,7 @@ iscsi_boot_create_kobj(struct iscsi_boot_kset *boot_kset, boot_kobj->kobj.kset = boot_kset->kset; if (kobject_init_and_add(&boot_kobj->kobj, &iscsi_boot_ktype, NULL, name, index)) { - kfree(boot_kobj); + kobject_put(&boot_kobj->kobj); return NULL; } boot_kobj->data = data; From 22dc1028afac9f41b073c76a4995451267572e2f Mon Sep 17 00:00:00 2001 From: Can Guo Date: Wed, 27 May 2020 19:24:42 -0700 Subject: [PATCH 109/162] scsi: ufs: Don't update urgent bkops level when toggling auto bkops [ Upstream commit be32acff43800c87dc5c707f5d47cc607b76b653 ] Urgent bkops level is used to compare against actual bkops status read from UFS device. Urgent bkops level is set during initialization and might be updated in exception event handler during runtime. But it should not be updated to the actual bkops status every time when auto bkops is toggled. Otherwise, if urgent bkops level is updated to 0, auto bkops shall always be kept enabled. Link: https://lore.kernel.org/r/1590632686-17866-1-git-send-email-cang@codeaurora.org Fixes: 24366c2afbb0 ("scsi: ufs: Recheck bkops level if bkops is disabled") Reviewed-by: Stanley Chu Signed-off-by: Can Guo Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ufs/ufshcd.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 3a98e5a1d830..1e2a97a10033 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -4890,7 +4890,6 @@ static int ufshcd_bkops_ctrl(struct ufs_hba *hba, err = ufshcd_enable_auto_bkops(hba); else err = ufshcd_disable_auto_bkops(hba); - hba->urgent_bkops_lvl = curr_status; out: return err; } From d9335c0f2d07c7d490493ea47f8698b0925b3e72 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 30 May 2020 22:19:52 +0200 Subject: [PATCH 110/162] pinctrl: imxl: Fix an error handling path in 'imx1_pinctrl_core_probe()' [ Upstream commit 9eb728321286c4b31e964d2377fca2368526d408 ] When 'pinctrl_register()' has been turned into 'devm_pinctrl_register()', an error handling path has not been updated. Axe a now unneeded 'pinctrl_unregister()'. Fixes: e55e025d1687 ("pinctrl: imxl: Use devm_pinctrl_register() for pinctrl registration") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/20200530201952.585798-1-christophe.jaillet@wanadoo.fr Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/freescale/pinctrl-imx1-core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c index e2cca91fd266..68108c4c3969 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c +++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c @@ -642,7 +642,6 @@ int imx1_pinctrl_core_probe(struct platform_device *pdev, ret = of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev); if (ret) { - pinctrl_unregister(ipctl->pctl); dev_err(&pdev->dev, "Failed to populate subdevices\n"); return ret; } From 0602d1bf15a76c17bb4dddee397e2492390c00fd Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 30 May 2020 22:49:55 +0200 Subject: [PATCH 111/162] pinctrl: freescale: imx: Fix an error handling path in 'imx_pinctrl_probe()' [ Upstream commit 11d8da5cabf7c6c3263ba2cd9c00260395867048 ] 'pinctrl_unregister()' should not be called to undo 'devm_pinctrl_register_and_init()', it is already handled by the framework. This simplifies the error handling paths of the probe function. The 'imx_free_resources()' can be removed as well. Fixes: a51c158bf0f7 ("pinctrl: imx: use radix trees for groups and functions") Signed-off-by: Christophe JAILLET Reviewed-by: Dong Aisheng Link: https://lore.kernel.org/r/20200530204955.588962-1-christophe.jaillet@wanadoo.fr Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/freescale/pinctrl-imx.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c index 17f2c5a505b2..ec0119e1e781 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx.c +++ b/drivers/pinctrl/freescale/pinctrl-imx.c @@ -661,16 +661,6 @@ static int imx_pinctrl_probe_dt(struct platform_device *pdev, return 0; } -/* - * imx_free_resources() - free memory used by this driver - * @info: info driver instance - */ -static void imx_free_resources(struct imx_pinctrl *ipctl) -{ - if (ipctl->pctl) - pinctrl_unregister(ipctl->pctl); -} - int imx_pinctrl_probe(struct platform_device *pdev, struct imx_pinctrl_soc_info *info) { @@ -761,21 +751,16 @@ int imx_pinctrl_probe(struct platform_device *pdev, &ipctl->pctl); if (ret) { dev_err(&pdev->dev, "could not register IMX pinctrl driver\n"); - goto free; + return ret; } ret = imx_pinctrl_probe_dt(pdev, ipctl); if (ret) { dev_err(&pdev->dev, "fail to probe dt properties\n"); - goto free; + return ret; } dev_info(&pdev->dev, "initialized IMX pinctrl driver\n"); return pinctrl_enable(ipctl->pctl); - -free: - imx_free_resources(ipctl); - - return ret; } From 49ce58ac440e104d9ce4009c020872c7be00c8c3 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 27 May 2020 15:24:29 +0300 Subject: [PATCH 112/162] crypto: omap-sham - add proper load balancing support for multicore [ Upstream commit 281c377872ff5d15d80df25fc4df02d2676c7cde ] The current implementation of the multiple accelerator core support for OMAP SHA does not work properly. It always picks up the first probed accelerator core if this is available, and rest of the book keeping also gets confused if there are two cores available. Add proper load balancing support for SHA, and also fix any bugs related to the multicore support while doing it. Signed-off-by: Tero Kristo Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/omap-sham.c | 64 ++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 33 deletions(-) diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c index c1f8da958c78..4e38b87c3228 100644 --- a/drivers/crypto/omap-sham.c +++ b/drivers/crypto/omap-sham.c @@ -168,8 +168,6 @@ struct omap_sham_hmac_ctx { }; struct omap_sham_ctx { - struct omap_sham_dev *dd; - unsigned long flags; /* fallback stuff */ @@ -916,27 +914,35 @@ static int omap_sham_update_dma_stop(struct omap_sham_dev *dd) return 0; } +struct omap_sham_dev *omap_sham_find_dev(struct omap_sham_reqctx *ctx) +{ + struct omap_sham_dev *dd; + + if (ctx->dd) + return ctx->dd; + + spin_lock_bh(&sham.lock); + dd = list_first_entry(&sham.dev_list, struct omap_sham_dev, list); + list_move_tail(&dd->list, &sham.dev_list); + ctx->dd = dd; + spin_unlock_bh(&sham.lock); + + return dd; +} + static int omap_sham_init(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct omap_sham_ctx *tctx = crypto_ahash_ctx(tfm); struct omap_sham_reqctx *ctx = ahash_request_ctx(req); - struct omap_sham_dev *dd = NULL, *tmp; + struct omap_sham_dev *dd; int bs = 0; - spin_lock_bh(&sham.lock); - if (!tctx->dd) { - list_for_each_entry(tmp, &sham.dev_list, list) { - dd = tmp; - break; - } - tctx->dd = dd; - } else { - dd = tctx->dd; - } - spin_unlock_bh(&sham.lock); + ctx->dd = NULL; - ctx->dd = dd; + dd = omap_sham_find_dev(ctx); + if (!dd) + return -ENODEV; ctx->flags = 0; @@ -1186,8 +1192,7 @@ err1: static int omap_sham_enqueue(struct ahash_request *req, unsigned int op) { struct omap_sham_reqctx *ctx = ahash_request_ctx(req); - struct omap_sham_ctx *tctx = crypto_tfm_ctx(req->base.tfm); - struct omap_sham_dev *dd = tctx->dd; + struct omap_sham_dev *dd = ctx->dd; ctx->op = op; @@ -1197,7 +1202,7 @@ static int omap_sham_enqueue(struct ahash_request *req, unsigned int op) static int omap_sham_update(struct ahash_request *req) { struct omap_sham_reqctx *ctx = ahash_request_ctx(req); - struct omap_sham_dev *dd = ctx->dd; + struct omap_sham_dev *dd = omap_sham_find_dev(ctx); if (!req->nbytes) return 0; @@ -1302,21 +1307,8 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key, struct omap_sham_hmac_ctx *bctx = tctx->base; int bs = crypto_shash_blocksize(bctx->shash); int ds = crypto_shash_digestsize(bctx->shash); - struct omap_sham_dev *dd = NULL, *tmp; int err, i; - spin_lock_bh(&sham.lock); - if (!tctx->dd) { - list_for_each_entry(tmp, &sham.dev_list, list) { - dd = tmp; - break; - } - tctx->dd = dd; - } else { - dd = tctx->dd; - } - spin_unlock_bh(&sham.lock); - err = crypto_shash_setkey(tctx->fallback, key, keylen); if (err) return err; @@ -1334,7 +1326,7 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key, memset(bctx->ipad + keylen, 0, bs - keylen); - if (!test_bit(FLAGS_AUTO_XOR, &dd->flags)) { + if (!test_bit(FLAGS_AUTO_XOR, &sham.flags)) { memcpy(bctx->opad, bctx->ipad, bs); for (i = 0; i < bs; i++) { @@ -2073,6 +2065,7 @@ static int omap_sham_probe(struct platform_device *pdev) } dd->flags |= dd->pdata->flags; + sham.flags |= dd->pdata->flags; pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY); @@ -2098,6 +2091,9 @@ static int omap_sham_probe(struct platform_device *pdev) spin_unlock(&sham.lock); for (i = 0; i < dd->pdata->algs_info_size; i++) { + if (dd->pdata->algs_info[i].registered) + break; + for (j = 0; j < dd->pdata->algs_info[i].size; j++) { struct ahash_alg *alg; @@ -2143,9 +2139,11 @@ static int omap_sham_remove(struct platform_device *pdev) list_del(&dd->list); spin_unlock(&sham.lock); for (i = dd->pdata->algs_info_size - 1; i >= 0; i--) - for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--) + for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--) { crypto_unregister_ahash( &dd->pdata->algs_info[i].algs_list[j]); + dd->pdata->algs_info[i].registered--; + } tasklet_kill(&dd->done_task); pm_runtime_disable(&pdev->dev); From f3ad0f4b86914874610663db3ec66a1054a96fe3 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Wed, 3 Jun 2020 11:12:14 +0200 Subject: [PATCH 113/162] geneve: change from tx_error to tx_dropped on missing metadata [ Upstream commit 9d149045b3c0e44c049cdbce8a64e19415290017 ] If the geneve interface is in collect_md (external) mode, it can't send any packets submitted directly to its net interface, as such packets won't have metadata attached. This is expected. However, the kernel itself sends some packets to the interface, most notably, IPv6 DAD, IPv6 multicast listener reports, etc. This is not wrong, as tunnel metadata can be specified in routing table (although technically, that has never worked for IPv6, but hopefully will be fixed eventually) and then the interface must correctly participate in IPv6 housekeeping. The problem is that any such attempt increases the tx_error counter. Just bringing up a geneve interface with IPv6 enabled is enough to see a number of tx_errors. That causes confusion among users, prompting them to find a network error where there is none. Change the counter used to tx_dropped. That better conveys the meaning (there's nothing wrong going on, just some packets are getting dropped) and hopefully will make admins panic less. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/geneve.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 6d3fa36b1616..3c9f8770f7e7 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -915,9 +915,10 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) if (geneve->collect_md) { info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { - err = -EINVAL; netdev_dbg(dev, "no tunnel metadata\n"); - goto tx_error; + dev_kfree_skb(skb); + dev->stats.tx_dropped++; + return NETDEV_TX_OK; } } else { info = &geneve->info; @@ -934,7 +935,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) if (likely(!err)) return NETDEV_TX_OK; -tx_error: + dev_kfree_skb(skb); if (err == -ELOOP) From 660915b3849c2574d7f7d100e1135aa9b38326dd Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 4 Jun 2020 16:50:17 -0700 Subject: [PATCH 114/162] lib/zlib: remove outdated and incorrect pre-increment optimization [ Upstream commit acaab7335bd6f0c0b54ce3a00bd7f18222ce0f5f ] The zlib inflate code has an old micro-optimization based on the assumption that for pre-increment memory accesses, the compiler will generate code that fits better into the processor's pipeline than what would be generated for post-increment memory accesses. This optimization was already removed in upstream zlib in 2016: https://github.com/madler/zlib/commit/9aaec95e8211 This optimization causes UB according to C99, which says in section 6.5.6 "Additive operators": "If both the pointer operand and the result point to elements of the same array object, or one past the last element of the array object, the evaluation shall not produce an overflow; otherwise, the behavior is undefined". This UB is not only a theoretical concern, but can also cause trouble for future work on compiler-based sanitizers. According to the zlib commit, this optimization also is not optimal anymore with modern compilers. Replace uses of OFF, PUP and UP_UNALIGNED with their definitions in the POSTINC case, and remove the macro definitions, just like in the upstream patch. Signed-off-by: Jann Horn Signed-off-by: Andrew Morton Cc: Mikhail Zaslonko Link: http://lkml.kernel.org/r/20200507123112.252723-1-jannh@google.com Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- lib/zlib_inflate/inffast.c | 91 +++++++++++++++----------------------- 1 file changed, 35 insertions(+), 56 deletions(-) diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c index 2c13ecc5bb2c..ed1f3df27260 100644 --- a/lib/zlib_inflate/inffast.c +++ b/lib/zlib_inflate/inffast.c @@ -10,17 +10,6 @@ #ifndef ASMINF -/* Allow machine dependent optimization for post-increment or pre-increment. - Based on testing to date, - Pre-increment preferred for: - - PowerPC G3 (Adler) - - MIPS R5000 (Randers-Pehrson) - Post-increment preferred for: - - none - No measurable difference: - - Pentium III (Anderson) - - M68060 (Nikl) - */ union uu { unsigned short us; unsigned char b[2]; @@ -38,16 +27,6 @@ get_unaligned16(const unsigned short *p) return mm.us; } -#ifdef POSTINC -# define OFF 0 -# define PUP(a) *(a)++ -# define UP_UNALIGNED(a) get_unaligned16((a)++) -#else -# define OFF 1 -# define PUP(a) *++(a) -# define UP_UNALIGNED(a) get_unaligned16(++(a)) -#endif - /* Decode literal, length, and distance codes and write out the resulting literal and match bytes until either not enough input or output is @@ -115,9 +94,9 @@ void inflate_fast(z_streamp strm, unsigned start) /* copy state to local variables */ state = (struct inflate_state *)strm->state; - in = strm->next_in - OFF; + in = strm->next_in; last = in + (strm->avail_in - 5); - out = strm->next_out - OFF; + out = strm->next_out; beg = out - (start - strm->avail_out); end = out + (strm->avail_out - 257); #ifdef INFLATE_STRICT @@ -138,9 +117,9 @@ void inflate_fast(z_streamp strm, unsigned start) input data or output space */ do { if (bits < 15) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } this = lcode[hold & lmask]; @@ -150,14 +129,14 @@ void inflate_fast(z_streamp strm, unsigned start) bits -= op; op = (unsigned)(this.op); if (op == 0) { /* literal */ - PUP(out) = (unsigned char)(this.val); + *out++ = (unsigned char)(this.val); } else if (op & 16) { /* length base */ len = (unsigned)(this.val); op &= 15; /* number of extra bits */ if (op) { if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } len += (unsigned)hold & ((1U << op) - 1); @@ -165,9 +144,9 @@ void inflate_fast(z_streamp strm, unsigned start) bits -= op; } if (bits < 15) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } this = dcode[hold & dmask]; @@ -180,10 +159,10 @@ void inflate_fast(z_streamp strm, unsigned start) dist = (unsigned)(this.val); op &= 15; /* number of extra bits */ if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } } @@ -205,13 +184,13 @@ void inflate_fast(z_streamp strm, unsigned start) state->mode = BAD; break; } - from = window - OFF; + from = window; if (write == 0) { /* very common case */ from += wsize - op; if (op < len) { /* some from window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } @@ -222,14 +201,14 @@ void inflate_fast(z_streamp strm, unsigned start) if (op < len) { /* some from end of window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); - from = window - OFF; + from = window; if (write < len) { /* some from start of window */ op = write; len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } @@ -240,21 +219,21 @@ void inflate_fast(z_streamp strm, unsigned start) if (op < len) { /* some from window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } while (len > 2) { - PUP(out) = PUP(from); - PUP(out) = PUP(from); - PUP(out) = PUP(from); + *out++ = *from++; + *out++ = *from++; + *out++ = *from++; len -= 3; } if (len) { - PUP(out) = PUP(from); + *out++ = *from++; if (len > 1) - PUP(out) = PUP(from); + *out++ = *from++; } } else { @@ -264,29 +243,29 @@ void inflate_fast(z_streamp strm, unsigned start) from = out - dist; /* copy direct from output */ /* minimum length is three */ /* Align out addr */ - if (!((long)(out - 1 + OFF) & 1)) { - PUP(out) = PUP(from); + if (!((long)(out - 1) & 1)) { + *out++ = *from++; len--; } - sout = (unsigned short *)(out - OFF); + sout = (unsigned short *)(out); if (dist > 2) { unsigned short *sfrom; - sfrom = (unsigned short *)(from - OFF); + sfrom = (unsigned short *)(from); loops = len >> 1; do #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - PUP(sout) = PUP(sfrom); + *sout++ = *sfrom++; #else - PUP(sout) = UP_UNALIGNED(sfrom); + *sout++ = get_unaligned16(sfrom++); #endif while (--loops); - out = (unsigned char *)sout + OFF; - from = (unsigned char *)sfrom + OFF; + out = (unsigned char *)sout; + from = (unsigned char *)sfrom; } else { /* dist == 1 or dist == 2 */ unsigned short pat16; - pat16 = *(sout-1+OFF); + pat16 = *(sout-1); if (dist == 1) { union uu mm; /* copy one char pattern to both bytes */ @@ -296,12 +275,12 @@ void inflate_fast(z_streamp strm, unsigned start) } loops = len >> 1; do - PUP(sout) = pat16; + *sout++ = pat16; while (--loops); - out = (unsigned char *)sout + OFF; + out = (unsigned char *)sout; } if (len & 1) - PUP(out) = PUP(from); + *out++ = *from++; } } else if ((op & 64) == 0) { /* 2nd level distance code */ @@ -336,8 +315,8 @@ void inflate_fast(z_streamp strm, unsigned start) hold &= (1U << bits) - 1; /* update state and return */ - strm->next_in = in + OFF; - strm->next_out = out + OFF; + strm->next_in = in; + strm->next_out = out; strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last)); strm->avail_out = (unsigned)(out < end ? 257 + (end - out) : 257 - (out - end)); From 7b192df913c914a277f05f82f618efeb4ac3f3ab Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 4 Jun 2020 16:50:30 -0700 Subject: [PATCH 115/162] include/linux/bitops.h: avoid clang shift-count-overflow warnings [ Upstream commit bd93f003b7462ae39a43c531abca37fe7073b866 ] Clang normally does not warn about certain issues in inline functions when it only happens in an eliminated code path. However if something else goes wrong, it does tend to complain about the definition of hweight_long() on 32-bit targets: include/linux/bitops.h:75:41: error: shift count >= width of type [-Werror,-Wshift-count-overflow] return sizeof(w) == 4 ? hweight32(w) : hweight64(w); ^~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:29:49: note: expanded from macro 'hweight64' define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) ^~~~~~~~~~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:21:76: note: expanded from macro '__const_hweight64' define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) ^ ~~ include/asm-generic/bitops/const_hweight.h:20:49: note: expanded from macro '__const_hweight32' define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) ^ include/asm-generic/bitops/const_hweight.h:19:72: note: expanded from macro '__const_hweight16' define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) ^ include/asm-generic/bitops/const_hweight.h:12:9: note: expanded from macro '__const_hweight8' (!!((w) & (1ULL << 2))) + \ Adding an explicit cast to __u64 avoids that warning and makes it easier to read other output. Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Acked-by: Christian Brauner Cc: Andy Shevchenko Cc: Rasmus Villemoes Cc: Josh Poimboeuf Cc: Nick Desaulniers Link: http://lkml.kernel.org/r/20200505135513.65265-1-arnd@arndb.de Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- include/linux/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bitops.h b/include/linux/bitops.h index c51574fab0b0..00dcb1bad76b 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -50,7 +50,7 @@ static inline int get_bitmask_order(unsigned int count) static __always_inline unsigned long hweight_long(unsigned long w) { - return sizeof(w) == 4 ? hweight32(w) : hweight64(w); + return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w); } /** From 5af24e3d94ad4706f8a42875ce88f6b20f55f37e Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 4 Jun 2020 16:50:49 -0700 Subject: [PATCH 116/162] elfnote: mark all .note sections SHF_ALLOC [ Upstream commit 51da9dfb7f20911ae4e79e9b412a9c2d4c373d4b ] ELFNOTE_START allows callers to specify flags for .pushsection assembler directives. All callsites but ELF_NOTE use "a" for SHF_ALLOC. For vdso's that explicitly use ELF_NOTE_START and BUILD_SALT, the same section is specified twice after preprocessing, once with "a" flag, once without. Example: .pushsection .note.Linux, "a", @note ; .pushsection .note.Linux, "", @note ; While GNU as allows this ordering, it warns for the opposite ordering, making these directives position dependent. We'd prefer not to precisely match this behavior in Clang's integrated assembler. Instead, the non __ASSEMBLY__ definition of ELF_NOTE uses __attribute__((section(".note.Linux"))) which is created with SHF_ALLOC, so let's make the __ASSEMBLY__ definition of ELF_NOTE consistent with C and just always use "a" flag. This allows Clang to assemble a working mainline (5.6) kernel via: $ make CC=clang AS=clang Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Reviewed-by: Nathan Chancellor Reviewed-by: Fangrui Song Cc: Jeremy Fitzhardinge Cc: Thomas Gleixner Cc: Vincenzo Frascino Link: https://github.com/ClangBuiltLinux/linux/issues/913 Link: http://lkml.kernel.org/r/20200325231250.99205-1-ndesaulniers@google.com Debugged-by: Ilie Halip Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- include/linux/elfnote.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index f236f5b931b2..7fdd7f355b52 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -54,7 +54,7 @@ .popsection ; #define ELFNOTE(name, type, desc) \ - ELFNOTE_START(name, type, "") \ + ELFNOTE_START(name, type, "a") \ desc ; \ ELFNOTE_END From a5cbb4a5f7f3a4beed32f6c66e8cdbf4999d5d53 Mon Sep 17 00:00:00 2001 From: Ram Pai Date: Thu, 4 Jun 2020 16:52:05 -0700 Subject: [PATCH 117/162] selftests/vm/pkeys: fix alloc_random_pkey() to make it really random [ Upstream commit 6e373263ce07eeaa6410843179535fbdf561fc31 ] alloc_random_pkey() was allocating the same pkey every time. Not all pkeys were geting tested. This fixes it. Signed-off-by: Ram Pai Signed-off-by: Sandipan Das Signed-off-by: Andrew Morton Acked-by: Dave Hansen Cc: Dave Hansen Cc: Florian Weimer Cc: "Desnes A. Nunes do Rosario" Cc: Ingo Molnar Cc: Thiago Jung Bauermann Cc: "Aneesh Kumar K.V" Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Suchanek Cc: Shuah Khan Link: http://lkml.kernel.org/r/0162f55816d4e783a0d6e49e554d0ab9a3c9a23b.1585646528.git.sandipan@linux.ibm.com Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- tools/testing/selftests/x86/protection_keys.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index 5d546dcdbc80..b8778960da10 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -24,6 +24,7 @@ #define _GNU_SOURCE #include #include +#include #include #include #include @@ -612,10 +613,10 @@ int alloc_random_pkey(void) int nr_alloced = 0; int random_index; memset(alloced_pkeys, 0, sizeof(alloced_pkeys)); + srand((unsigned int)time(NULL)); /* allocate every possible key and make a note of which ones we got */ max_nr_pkey_allocs = NR_PKEYS; - max_nr_pkey_allocs = 1; for (i = 0; i < max_nr_pkey_allocs; i++) { int new_pkey = alloc_pkey(); if (new_pkey < 0) From 96e4245f62e2904801da16a87f537d3570551f2c Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Thu, 4 Jun 2020 00:13:28 -0700 Subject: [PATCH 118/162] blktrace: use errno instead of bi_status [ Upstream commit 48bc3cd3e07a1486f45d9971c75d6090976c3b1b ] In blk_add_trace_spliti() blk_add_trace_bio_remap() use blk_status_to_errno() to pass the error instead of pasing the bi_status. This fixes the sparse warning. Signed-off-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- kernel/trace/blktrace.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index a60c09e0bda8..30a98156f474 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1022,8 +1022,10 @@ static void blk_add_trace_split(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, - BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), - &rpdu, blk_trace_bio_get_cgid(q, bio)); + BLK_TA_SPLIT, + blk_status_to_errno(bio->bi_status), + sizeof(rpdu), &rpdu, + blk_trace_bio_get_cgid(q, bio)); } rcu_read_unlock(); } @@ -1060,7 +1062,8 @@ static void blk_add_trace_bio_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, + blk_status_to_errno(bio->bi_status), sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } From d29759068559c9b32b21845beab14016b759f248 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Thu, 4 Jun 2020 00:13:29 -0700 Subject: [PATCH 119/162] blktrace: fix endianness in get_pdu_int() [ Upstream commit 71df3fd82e7cccec7b749a8607a4662d9f7febdd ] In function get_pdu_len() replace variable type from __u64 to __be64. This fixes sparse warning. Signed-off-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- kernel/trace/blktrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 30a98156f474..be97e0b4ae7d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1285,7 +1285,7 @@ static inline __u16 t_error(const struct trace_entry *ent) static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { - const __u64 *val = pdu_start(ent, has_cg); + const __be64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } From ce5a0d403f8c9507240ea55e7fc2ff9843ac2a01 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Thu, 4 Jun 2020 00:13:30 -0700 Subject: [PATCH 120/162] blktrace: fix endianness for blk_log_remap() [ Upstream commit 5aec598c456fe3c1b71a1202cbb42bdc2a643277 ] The function blk_log_remap() can be simplified by removing the call to get_pdu_remap() that copies the values into extra variable to print the data, which also fixes the endiannness warning reported by sparse. Signed-off-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- kernel/trace/blktrace.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index be97e0b4ae7d..304a164f5e7e 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1289,17 +1289,6 @@ static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) return be64_to_cpu(*val); } -static void get_pdu_remap(const struct trace_entry *ent, - struct blk_io_trace_remap *r, bool has_cg) -{ - const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); - __u64 sector_from = __r->sector_from; - - r->device_from = be32_to_cpu(__r->device_from); - r->device_to = be32_to_cpu(__r->device_to); - r->sector_from = be64_to_cpu(sector_from); -} - typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, bool has_cg); @@ -1425,13 +1414,13 @@ static void blk_log_with_error(struct trace_seq *s, static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { - struct blk_io_trace_remap r = { .device_from = 0, }; + const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); - get_pdu_remap(ent, &r, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), - MAJOR(r.device_from), MINOR(r.device_from), - (unsigned long long)r.sector_from); + MAJOR(be32_to_cpu(__r->device_from)), + MINOR(be32_to_cpu(__r->device_from)), + be64_to_cpu(__r->sector_from)); } static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) From 04017f6617296fb5fc95c8f0f11dea3297ad6ad0 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Thu, 4 Jun 2020 14:28:58 -0500 Subject: [PATCH 121/162] gfs2: fix use-after-free on transaction ail lists [ Upstream commit 83d060ca8d90fa1e3feac227f995c013100862d3 ] Before this patch, transactions could be merged into the system transaction by function gfs2_merge_trans(), but the transaction ail lists were never merged. Because the ail flushing mechanism can run separately, bd elements can be attached to the transaction's buffer list during the transaction (trans_add_meta, etc) but quickly moved to its ail lists. Later, in function gfs2_trans_end, the transaction can be freed (by gfs2_trans_end) while it still has bd elements queued to its ail lists, which can cause it to either lose track of the bd elements altogether (memory leak) or worse, reference the bd elements after the parent transaction has been freed. Although I've not seen any serious consequences, the problem becomes apparent with the previous patch's addition of: gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list)); to function gfs2_trans_free(). This patch adds logic into gfs2_merge_trans() to move the merged transaction's ail lists to the sdp transaction. This prevents the use-after-free. To do this properly, we need to hold the ail lock, so we pass sdp into the function instead of the transaction itself. Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/log.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index a3208511f35a..f30418911e1b 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -804,8 +804,10 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, * @new: New transaction to be merged */ -static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new) +static void gfs2_merge_trans(struct gfs2_sbd *sdp, struct gfs2_trans *new) { + struct gfs2_trans *old = sdp->sd_log_tr; + WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags)); old->tr_num_buf_new += new->tr_num_buf_new; @@ -817,6 +819,11 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new) list_splice_tail_init(&new->tr_databuf, &old->tr_databuf); list_splice_tail_init(&new->tr_buf, &old->tr_buf); + + spin_lock(&sdp->sd_ail_lock); + list_splice_tail_init(&new->tr_ail1_list, &old->tr_ail1_list); + list_splice_tail_init(&new->tr_ail2_list, &old->tr_ail2_list); + spin_unlock(&sdp->sd_ail_lock); } static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) @@ -828,7 +835,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_log_lock(sdp); if (sdp->sd_log_tr) { - gfs2_merge_trans(sdp->sd_log_tr, tr); + gfs2_merge_trans(sdp, tr); } else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) { gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags)); sdp->sd_log_tr = tr; From dbc1d98be18a813778c30bab352627be16f29762 Mon Sep 17 00:00:00 2001 From: tannerlove Date: Mon, 8 Jun 2020 15:37:15 -0400 Subject: [PATCH 122/162] selftests/net: in timestamping, strncpy needs to preserve null byte MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8027bc0307ce59759b90679fa5d8b22949586d20 ] If user passed an interface option longer than 15 characters, then device.ifr_name and hwtstamp.ifr_name became non-null-terminated strings. The compiler warned about this: timestamping.c:353:2: warning: ‘strncpy’ specified bound 16 equals \ destination size [-Wstringop-truncation] 353 | strncpy(device.ifr_name, interface, sizeof(device.ifr_name)); Fixes: cb9eff097831 ("net: new user space API for time stamping of incoming and outgoing packets") Signed-off-by: Tanner Love Acked-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../selftests/networking/timestamping/timestamping.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/networking/timestamping/timestamping.c b/tools/testing/selftests/networking/timestamping/timestamping.c index 5cdfd743447b..900ed4b47899 100644 --- a/tools/testing/selftests/networking/timestamping/timestamping.c +++ b/tools/testing/selftests/networking/timestamping/timestamping.c @@ -332,10 +332,16 @@ int main(int argc, char **argv) int val; socklen_t len; struct timeval next; + size_t if_len; if (argc < 2) usage(0); interface = argv[1]; + if_len = strlen(interface); + if (if_len >= IFNAMSIZ) { + printf("interface name exceeds IFNAMSIZ\n"); + exit(1); + } for (i = 2; i < argc; i++) { if (!strcasecmp(argv[i], "SO_TIMESTAMP")) @@ -369,12 +375,12 @@ int main(int argc, char **argv) bail("socket"); memset(&device, 0, sizeof(device)); - strncpy(device.ifr_name, interface, sizeof(device.ifr_name)); + memcpy(device.ifr_name, interface, if_len + 1); if (ioctl(sock, SIOCGIFADDR, &device) < 0) bail("getting interface IP address"); memset(&hwtstamp, 0, sizeof(hwtstamp)); - strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name)); + memcpy(hwtstamp.ifr_name, interface, if_len + 1); hwtstamp.ifr_data = (void *)&hwconfig; memset(&hwconfig, 0, sizeof(hwconfig)); hwconfig.tx_type = From c6987aa74a9d589b8547bfde5a55ef26ba65e5af Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Mon, 13 Apr 2020 11:54:57 +0200 Subject: [PATCH 123/162] drm/sun4i: hdmi ddc clk: Fix size of m divider [ Upstream commit 54e1e06bcf1cf6e7ac3f86daa5f7454add24b494 ] m divider in DDC clock register is 4 bits wide. Fix that. Fixes: 9c5681011a0c ("drm/sun4i: Add HDMI support") Signed-off-by: Jernej Skrabec Reviewed-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20200413095457.1176754-1-jernej.skrabec@siol.net Signed-off-by: Sasha Levin --- drivers/gpu/drm/sun4i/sun4i_hdmi.h | 2 +- drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h index a1f8cba251a2..3d9148eb40a7 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h @@ -143,7 +143,7 @@ #define SUN4I_HDMI_DDC_CMD_IMPLICIT_WRITE 3 #define SUN4I_HDMI_DDC_CLK_REG 0x528 -#define SUN4I_HDMI_DDC_CLK_M(m) (((m) & 0x7) << 3) +#define SUN4I_HDMI_DDC_CLK_M(m) (((m) & 0xf) << 3) #define SUN4I_HDMI_DDC_CLK_N(n) ((n) & 0x7) #define SUN4I_HDMI_DDC_LINE_CTRL_REG 0x540 diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c index 4692e8c345ed..58d9557a774f 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c @@ -32,7 +32,7 @@ static unsigned long sun4i_ddc_calc_divider(unsigned long rate, unsigned long best_rate = 0; u8 best_m = 0, best_n = 0, _m, _n; - for (_m = 0; _m < 8; _m++) { + for (_m = 0; _m < 16; _m++) { for (_n = 0; _n < 8; _n++) { unsigned long tmp_rate; From a2c3d7701f4a160c187e5b07e89e52993b0c0abf Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 30 May 2020 10:16:22 +0200 Subject: [PATCH 124/162] scsi: acornscsi: Fix an error handling path in acornscsi_probe() [ Upstream commit 42c76c9848e13dbe0538d7ae0147a269dfa859cb ] 'ret' is known to be 0 at this point. Explicitly return -ENOMEM if one of the 'ecardm_iomap()' calls fail. Link: https://lore.kernel.org/r/20200530081622.577888-1-christophe.jaillet@wanadoo.fr Fixes: e95a1b656a98 ("[ARM] rpc: acornscsi: update to new style ecard driver") Signed-off-by: Christophe JAILLET Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/arm/acornscsi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c index 421fe869a11e..ef9d907f2df5 100644 --- a/drivers/scsi/arm/acornscsi.c +++ b/drivers/scsi/arm/acornscsi.c @@ -2914,8 +2914,10 @@ static int acornscsi_probe(struct expansion_card *ec, const struct ecard_id *id) ashost->base = ecardm_iomap(ec, ECARD_RES_MEMC, 0, 0); ashost->fast = ecardm_iomap(ec, ECARD_RES_IOCFAST, 0, 0); - if (!ashost->base || !ashost->fast) + if (!ashost->base || !ashost->fast) { + ret = -ENOMEM; goto out_put; + } host->irq = ec->irq; ashost->host = host; From 9f33eff4958885f6fd64c18221c36d065ef8ba8a Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 18 May 2020 16:49:30 +0100 Subject: [PATCH 125/162] usb/xhci-plat: Set PM runtime as active on resume [ Upstream commit 79112cc3c29f4a8c73a21428fbcbcb0afb005e3e ] Follow suit of ohci-platform.c and perform pm_runtime_set_active() on resume. ohci-platform.c had a warning reported due to the missing pm_runtime_set_active() [1]. [1] https://lore.kernel.org/lkml/20200323143857.db5zphxhq4hz3hmd@e107158-lin.cambridge.arm.com/ Signed-off-by: Qais Yousef CC: Tony Prisk CC: Greg Kroah-Hartman CC: Mathias Nyman CC: Oliver Neukum CC: linux-arm-kernel@lists.infradead.org CC: linux-usb@vger.kernel.org CC: linux-kernel@vger.kernel.org Link: https://lore.kernel.org/r/20200518154931.6144-2-qais.yousef@arm.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-plat.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 2a73592908e1..7219cbf7c54c 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -381,7 +381,15 @@ static int __maybe_unused xhci_plat_resume(struct device *dev) if (ret) return ret; - return xhci_resume(xhci, 0); + ret = xhci_resume(xhci, 0); + if (ret) + return ret; + + pm_runtime_disable(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + + return 0; } static int __maybe_unused xhci_plat_runtime_suspend(struct device *dev) From 5410d158ca2a50bcf3f48c57f6cd73f4cf479e69 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 18 May 2020 16:49:31 +0100 Subject: [PATCH 126/162] usb/ehci-platform: Set PM runtime as active on resume [ Upstream commit 16bdc04cc98ab0c74392ceef2475ecc5e73fcf49 ] Follow suit of ohci-platform.c and perform pm_runtime_set_active() on resume. ohci-platform.c had a warning reported due to the missing pm_runtime_set_active() [1]. [1] https://lore.kernel.org/lkml/20200323143857.db5zphxhq4hz3hmd@e107158-lin.cambridge.arm.com/ Acked-by: Alan Stern Signed-off-by: Qais Yousef CC: Tony Prisk CC: Greg Kroah-Hartman CC: Mathias Nyman CC: Oliver Neukum CC: linux-arm-kernel@lists.infradead.org CC: linux-usb@vger.kernel.org CC: linux-kernel@vger.kernel.org Link: https://lore.kernel.org/r/20200518154931.6144-3-qais.yousef@arm.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/ehci-platform.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c index f1908ea9fbd8..6fcd33288014 100644 --- a/drivers/usb/host/ehci-platform.c +++ b/drivers/usb/host/ehci-platform.c @@ -390,6 +390,11 @@ static int ehci_platform_resume(struct device *dev) } ehci_resume(hcd, priv->reset_on_resume); + + pm_runtime_disable(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + return 0; } #endif /* CONFIG_PM_SLEEP */ From 4e92c1239c13b29d248c9292955cb3526f0add42 Mon Sep 17 00:00:00 2001 From: Gaurav Singh Date: Mon, 8 Jun 2020 13:18:17 -0300 Subject: [PATCH 127/162] perf report: Fix NULL pointer dereference in hists__fprintf_nr_sample_events() [ Upstream commit 11b6e5482e178055ec1f2444b55f2518713809d1 ] The 'evname' variable can be NULL, as it is checked a few lines back, check it before using. Fixes: 9e207ddfa207 ("perf report: Show call graph from reference events") Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/ Signed-off-by: Gaurav Singh Signed-off-by: Sasha Levin --- tools/perf/builtin-report.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 429c3e140dc3..35a10b598544 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -401,8 +401,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report if (evname != NULL) ret += fprintf(fp, " of event '%s'", evname); - if (symbol_conf.show_ref_callgraph && - strstr(evname, "call-graph=no")) { + if (symbol_conf.show_ref_callgraph && evname && strstr(evname, "call-graph=no")) { ret += fprintf(fp, ", show reference callgraph"); } From 80d90125a3e1c98aafb6b13e62bd680fe9a4cd5a Mon Sep 17 00:00:00 2001 From: Zhiqiang Liu Date: Mon, 15 Jun 2020 00:53:30 +0800 Subject: [PATCH 128/162] bcache: fix potential deadlock problem in btree_gc_coalesce [ Upstream commit be23e837333a914df3f24bf0b32e87b0331ab8d1 ] coccicheck reports: drivers/md//bcache/btree.c:1538:1-7: preceding lock on line 1417 In btree_gc_coalesce func, if the coalescing process fails, we will goto to out_nocoalesce tag directly without releasing new_nodes[i]->write_lock. Then, it will cause a deadlock when trying to acquire new_nodes[i]-> write_lock for freeing new_nodes[i] before return. btree_gc_coalesce func details as follows: if alloc new_nodes[i] fails: goto out_nocoalesce; // obtain new_nodes[i]->write_lock mutex_lock(&new_nodes[i]->write_lock) // main coalescing process for (i = nodes - 1; i > 0; --i) [snipped] if coalescing process fails: // Here, directly goto out_nocoalesce // tag will cause a deadlock goto out_nocoalesce; [snipped] // release new_nodes[i]->write_lock mutex_unlock(&new_nodes[i]->write_lock) // coalesing succ, return return; out_nocoalesce: btree_node_free(new_nodes[i]) // free new_nodes[i] // obtain new_nodes[i]->write_lock mutex_lock(&new_nodes[i]->write_lock); // set flag for reuse clear_bit(BTREE_NODE_dirty, &ew_nodes[i]->flags); // release new_nodes[i]->write_lock mutex_unlock(&new_nodes[i]->write_lock); To fix the problem, we add a new tag 'out_unlock_nocoalesce' for releasing new_nodes[i]->write_lock before out_nocoalesce tag. If coalescing process fails, we will go to out_unlock_nocoalesce tag for releasing new_nodes[i]->write_lock before free new_nodes[i] in out_nocoalesce tag. (Coly Li helps to clean up commit log format.) Fixes: 2a285686c109816 ("bcache: btree locking rework") Signed-off-by: Zhiqiang Liu Signed-off-by: Coly Li Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/md/bcache/btree.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 96a6583e7b52..66c764491a83 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1374,7 +1374,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, if (__set_blocks(n1, n1->keys + n2->keys, block_bytes(b->c)) > btree_blocks(new_nodes[i])) - goto out_nocoalesce; + goto out_unlock_nocoalesce; keys = n2->keys; /* Take the key of the node we're getting rid of */ @@ -1403,7 +1403,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, if (__bch_keylist_realloc(&keylist, bkey_u64s(&new_nodes[i]->key))) - goto out_nocoalesce; + goto out_unlock_nocoalesce; bch_btree_node_write(new_nodes[i], &cl); bch_keylist_add(&keylist, &new_nodes[i]->key); @@ -1449,6 +1449,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, /* Invalidated our iterator */ return -EINTR; +out_unlock_nocoalesce: + for (i = 0; i < nodes; i++) + mutex_unlock(&new_nodes[i]->write_lock); + out_nocoalesce: closure_sync(&cl); bch_keylist_free(&keylist); From a43abf15844c9e5de016957b8e612f447b7fb077 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Tue, 16 Jun 2020 20:16:55 +0800 Subject: [PATCH 129/162] block: Fix use-after-free in blkdev_get() [ Upstream commit 2d3a8e2deddea6c89961c422ec0c5b851e648c14 ] In blkdev_get() we call __blkdev_get() to do some internal jobs and if there is some errors in __blkdev_get(), the bdput() is called which means we have released the refcount of the bdev (actually the refcount of the bdev inode). This means we cannot access bdev after that point. But acctually bdev is still accessed in blkdev_get() after calling __blkdev_get(). This results in use-after-free if the refcount is the last one we released in __blkdev_get(). Let's take a look at the following scenerio: CPU0 CPU1 CPU2 blkdev_open blkdev_open Remove disk bd_acquire blkdev_get __blkdev_get del_gendisk bdev_unhash_inode bd_acquire bdev_get_gendisk bd_forget failed because of unhashed bdput bdput (the last one) bdev_evict_inode access bdev => use after free [ 459.350216] BUG: KASAN: use-after-free in __lock_acquire+0x24c1/0x31b0 [ 459.351190] Read of size 8 at addr ffff88806c815a80 by task syz-executor.0/20132 [ 459.352347] [ 459.352594] CPU: 0 PID: 20132 Comm: syz-executor.0 Not tainted 4.19.90 #2 [ 459.353628] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 459.354947] Call Trace: [ 459.355337] dump_stack+0x111/0x19e [ 459.355879] ? __lock_acquire+0x24c1/0x31b0 [ 459.356523] print_address_description+0x60/0x223 [ 459.357248] ? __lock_acquire+0x24c1/0x31b0 [ 459.357887] kasan_report.cold+0xae/0x2d8 [ 459.358503] __lock_acquire+0x24c1/0x31b0 [ 459.359120] ? _raw_spin_unlock_irq+0x24/0x40 [ 459.359784] ? lockdep_hardirqs_on+0x37b/0x580 [ 459.360465] ? _raw_spin_unlock_irq+0x24/0x40 [ 459.361123] ? finish_task_switch+0x125/0x600 [ 459.361812] ? finish_task_switch+0xee/0x600 [ 459.362471] ? mark_held_locks+0xf0/0xf0 [ 459.363108] ? __schedule+0x96f/0x21d0 [ 459.363716] lock_acquire+0x111/0x320 [ 459.364285] ? blkdev_get+0xce/0xbe0 [ 459.364846] ? blkdev_get+0xce/0xbe0 [ 459.365390] __mutex_lock+0xf9/0x12a0 [ 459.365948] ? blkdev_get+0xce/0xbe0 [ 459.366493] ? bdev_evict_inode+0x1f0/0x1f0 [ 459.367130] ? blkdev_get+0xce/0xbe0 [ 459.367678] ? destroy_inode+0xbc/0x110 [ 459.368261] ? mutex_trylock+0x1a0/0x1a0 [ 459.368867] ? __blkdev_get+0x3e6/0x1280 [ 459.369463] ? bdev_disk_changed+0x1d0/0x1d0 [ 459.370114] ? blkdev_get+0xce/0xbe0 [ 459.370656] blkdev_get+0xce/0xbe0 [ 459.371178] ? find_held_lock+0x2c/0x110 [ 459.371774] ? __blkdev_get+0x1280/0x1280 [ 459.372383] ? lock_downgrade+0x680/0x680 [ 459.373002] ? lock_acquire+0x111/0x320 [ 459.373587] ? bd_acquire+0x21/0x2c0 [ 459.374134] ? do_raw_spin_unlock+0x4f/0x250 [ 459.374780] blkdev_open+0x202/0x290 [ 459.375325] do_dentry_open+0x49e/0x1050 [ 459.375924] ? blkdev_get_by_dev+0x70/0x70 [ 459.376543] ? __x64_sys_fchdir+0x1f0/0x1f0 [ 459.377192] ? inode_permission+0xbe/0x3a0 [ 459.377818] path_openat+0x148c/0x3f50 [ 459.378392] ? kmem_cache_alloc+0xd5/0x280 [ 459.379016] ? entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 459.379802] ? path_lookupat.isra.0+0x900/0x900 [ 459.380489] ? __lock_is_held+0xad/0x140 [ 459.381093] do_filp_open+0x1a1/0x280 [ 459.381654] ? may_open_dev+0xf0/0xf0 [ 459.382214] ? find_held_lock+0x2c/0x110 [ 459.382816] ? lock_downgrade+0x680/0x680 [ 459.383425] ? __lock_is_held+0xad/0x140 [ 459.384024] ? do_raw_spin_unlock+0x4f/0x250 [ 459.384668] ? _raw_spin_unlock+0x1f/0x30 [ 459.385280] ? __alloc_fd+0x448/0x560 [ 459.385841] do_sys_open+0x3c3/0x500 [ 459.386386] ? filp_open+0x70/0x70 [ 459.386911] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 459.387610] ? trace_hardirqs_off_caller+0x55/0x1c0 [ 459.388342] ? do_syscall_64+0x1a/0x520 [ 459.388930] do_syscall_64+0xc3/0x520 [ 459.389490] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 459.390248] RIP: 0033:0x416211 [ 459.390720] Code: 75 14 b8 02 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 04 19 00 00 c3 48 83 ec 08 e8 0a fa ff ff 48 89 04 24 b8 02 00 00 00 0f 05 <48> 8b 3c 24 48 89 c2 e8 53 fa ff ff 48 89 d0 48 83 c4 08 48 3d 01 [ 459.393483] RSP: 002b:00007fe45dfe9a60 EFLAGS: 00000293 ORIG_RAX: 0000000000000002 [ 459.394610] RAX: ffffffffffffffda RBX: 00007fe45dfea6d4 RCX: 0000000000416211 [ 459.395678] RDX: 00007fe45dfe9b0a RSI: 0000000000000002 RDI: 00007fe45dfe9b00 [ 459.396758] RBP: 000000000076bf20 R08: 0000000000000000 R09: 000000000000000a [ 459.397930] R10: 0000000000000075 R11: 0000000000000293 R12: 00000000ffffffff [ 459.399022] R13: 0000000000000bd9 R14: 00000000004cdb80 R15: 000000000076bf2c [ 459.400168] [ 459.400430] Allocated by task 20132: [ 459.401038] kasan_kmalloc+0xbf/0xe0 [ 459.401652] kmem_cache_alloc+0xd5/0x280 [ 459.402330] bdev_alloc_inode+0x18/0x40 [ 459.402970] alloc_inode+0x5f/0x180 [ 459.403510] iget5_locked+0x57/0xd0 [ 459.404095] bdget+0x94/0x4e0 [ 459.404607] bd_acquire+0xfa/0x2c0 [ 459.405113] blkdev_open+0x110/0x290 [ 459.405702] do_dentry_open+0x49e/0x1050 [ 459.406340] path_openat+0x148c/0x3f50 [ 459.406926] do_filp_open+0x1a1/0x280 [ 459.407471] do_sys_open+0x3c3/0x500 [ 459.408010] do_syscall_64+0xc3/0x520 [ 459.408572] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 459.409415] [ 459.409679] Freed by task 1262: [ 459.410212] __kasan_slab_free+0x129/0x170 [ 459.410919] kmem_cache_free+0xb2/0x2a0 [ 459.411564] rcu_process_callbacks+0xbb2/0x2320 [ 459.412318] __do_softirq+0x225/0x8ac Fix this by delaying bdput() to the end of blkdev_get() which means we have finished accessing bdev. Fixes: 77ea887e433a ("implement in-kernel gendisk events handling") Reported-by: Hulk Robot Signed-off-by: Jason Yan Tested-by: Sedat Dilek Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Reviewed-by: Dan Carpenter Cc: Christoph Hellwig Cc: Jens Axboe Cc: Ming Lei Cc: Jan Kara Cc: Dan Carpenter Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- fs/block_dev.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 61949e3446e5..77ce77a28324 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1439,10 +1439,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) */ if (!for_part) { ret = devcgroup_inode_permission(bdev->bd_inode, perm); - if (ret != 0) { - bdput(bdev); + if (ret != 0) return ret; - } } restart: @@ -1515,8 +1513,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; BUG_ON(for_part); ret = __blkdev_get(whole, mode, 1); - if (ret) + if (ret) { + bdput(whole); goto out_clear; + } bdev->bd_contains = whole; bdev->bd_part = disk_get_part(disk, partno); if (!(disk->flags & GENHD_FL_UP) || @@ -1570,7 +1570,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) put_disk(disk); module_put(owner); out: - bdput(bdev); return ret; } @@ -1656,6 +1655,9 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) bdput(whole); } + if (res) + bdput(bdev); + return res; } EXPORT_SYMBOL(blkdev_get); From 125de1ce27a04609be11d1ec9c3ee4b9a1ef633a Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 29 May 2020 14:12:18 +0100 Subject: [PATCH 130/162] arm64: hw_breakpoint: Don't invoke overflow handler on uaccess watchpoints [ Upstream commit 24ebec25fb270100e252b19c288e21bd7d8cc7f7 ] Unprivileged memory accesses generated by the so-called "translated" instructions (e.g. STTR) at EL1 can cause EL0 watchpoints to fire unexpectedly if kernel debugging is enabled. In such cases, the hw_breakpoint logic will invoke the user overflow handler which will typically raise a SIGTRAP back to the current task. This is futile when returning back to the kernel because (a) the signal won't have been delivered and (b) userspace can't handle the thing anyway. Avoid invoking the user overflow handler for watchpoints triggered by kernel uaccess routines, and instead single-step over the faulting instruction as we would if no overflow handler had been installed. (Fixes tag identifies the introduction of unprivileged memory accesses, which exposed this latent bug in the hw_breakpoint code) Cc: Catalin Marinas Cc: James Morse Fixes: 57f4959bad0a ("arm64: kernel: Add support for User Access Override") Reported-by: Luis Machado Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/kernel/hw_breakpoint.c | 44 ++++++++++++++++++------------- 1 file changed, 26 insertions(+), 18 deletions(-) diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 95697a9c1245..6e96cea99a4e 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -738,6 +738,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -747,7 +768,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -785,25 +805,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step) From cebfb7caf25eff24a73a93e7910c59047e6eb1a6 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Wed, 3 Jun 2020 15:48:19 +0800 Subject: [PATCH 131/162] libata: Use per port sync for detach [ Upstream commit b5292111de9bb70cba3489075970889765302136 ] Commit 130f4caf145c ("libata: Ensure ata_port probe has completed before detach") may cause system freeze during suspend. Using async_synchronize_full() in PM callbacks is wrong, since async callbacks that are already scheduled may wait for not-yet-scheduled callbacks, causes a circular dependency. Instead of using big hammer like async_synchronize_full(), use async cookie to make sure port probe are synced, without affecting other scheduled PM callbacks. Fixes: 130f4caf145c ("libata: Ensure ata_port probe has completed before detach") Suggested-by: John Garry Signed-off-by: Kai-Heng Feng Tested-by: John Garry BugLink: https://bugs.launchpad.net/bugs/1867983 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/ata/libata-core.c | 11 +++++------ include/linux/libata.h | 3 +++ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 33eb5e342a7a..a3a65f5490c0 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -57,7 +57,6 @@ #include #include #include -#include #include #include #include @@ -6536,7 +6535,7 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) /* perform each probe asynchronously */ for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; - async_schedule(async_port_probe, ap); + ap->cookie = async_schedule(async_port_probe, ap); } return 0; @@ -6676,11 +6675,11 @@ void ata_host_detach(struct ata_host *host) { int i; - /* Ensure ata_port probe has completed */ - async_synchronize_full(); - - for (i = 0; i < host->n_ports; i++) + for (i = 0; i < host->n_ports; i++) { + /* Ensure ata_port probe has completed */ + async_synchronize_cookie(host->ports[i]->cookie + 1); ata_port_detach(host->ports[i]); + } /* the host is dead now, dissociate ACPI */ ata_acpi_dissociate(host); diff --git a/include/linux/libata.h b/include/linux/libata.h index 93838d98e3f3..5c9a44e3a027 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -38,6 +38,7 @@ #include #include #include +#include /* * Define if arch has non-standard setup. This is a _PCI_ standard @@ -884,6 +885,8 @@ struct ata_port { struct timer_list fastdrain_timer; unsigned long fastdrain_cnt; + async_cookie_t cookie; + int em_message_type; void *private_data; From 8d4b53d74adbdceda49e6e47263abde246cde0b1 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 15 Jun 2020 09:58:10 +0200 Subject: [PATCH 132/162] drm: encoder_slave: fix refcouting error for modules [ Upstream commit f78d4032de60f50fd4afaa0fb68ea03b985f820a ] module_put() balances try_module_get(), not request_module(). Fix the error path to match that. Fixes: 2066facca4c7 ("drm/kms: slave encoder interface.") Signed-off-by: Wolfram Sang Reviewed-by: Emil Velikov Acked-by: Daniel Vetter Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_encoder_slave.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c index cf804389f5ec..d50a7884e69e 100644 --- a/drivers/gpu/drm/drm_encoder_slave.c +++ b/drivers/gpu/drm/drm_encoder_slave.c @@ -84,7 +84,7 @@ int drm_i2c_encoder_init(struct drm_device *dev, err = encoder_drv->encoder_init(client, dev, encoder); if (err) - goto fail_unregister; + goto fail_module_put; if (info->platform_data) encoder->slave_funcs->set_config(&encoder->base, @@ -92,9 +92,10 @@ int drm_i2c_encoder_init(struct drm_device *dev, return 0; +fail_module_put: + module_put(module); fail_unregister: i2c_unregister_device(client); - module_put(module); fail: return err; } From 7ee3c3e77fd0dbd7ae7361d969df45e8dbe236bb Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Fri, 3 Apr 2020 14:08:32 -0400 Subject: [PATCH 133/162] drm/dp_mst: Reformat drm_dp_check_act_status() a bit commit a5cb5fa6c3a5c2cf492db667b8670ee7b044b79f upstream. Just add a bit more line wrapping, get rid of some extraneous whitespace, remove an unneeded goto label, and move around some variable declarations. No functional changes here. Signed-off-by: Lyude Paul [this isn't a fix, but it's needed for the fix that comes after this] Fixes: ad7f8a1f9ced ("drm/helper: add Displayport multi-stream helper (v0.6)") Cc: Sean Paul Cc: # v3.17+ Reviewed-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200406221253.1307209-3-lyude@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_dp_mst_topology.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 42eaeae86bb8..df5d853f96ee 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -2760,33 +2760,31 @@ fail: */ int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr) { + int count = 0, ret; u8 status; - int ret; - int count = 0; do { - ret = drm_dp_dpcd_readb(mgr->aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status); - + ret = drm_dp_dpcd_readb(mgr->aux, + DP_PAYLOAD_TABLE_UPDATE_STATUS, + &status); if (ret < 0) { - DRM_DEBUG_KMS("failed to read payload table status %d\n", ret); - goto fail; + DRM_DEBUG_KMS("failed to read payload table status %d\n", + ret); + return ret; } if (status & DP_PAYLOAD_ACT_HANDLED) break; count++; udelay(100); - } while (count < 30); if (!(status & DP_PAYLOAD_ACT_HANDLED)) { - DRM_DEBUG_KMS("failed to get ACT bit %d after %d retries\n", status, count); - ret = -EINVAL; - goto fail; + DRM_DEBUG_KMS("failed to get ACT bit %d after %d retries\n", + status, count); + return -EINVAL; } return 0; -fail: - return ret; } EXPORT_SYMBOL(drm_dp_check_act_status); From 08d6496c78468967eedbcf2f8b4002db0edfd217 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 Mar 2020 14:18:08 +0800 Subject: [PATCH 134/162] drm/qxl: Use correct notify port address when creating cursor ring commit 80e5f89da3ab949fbbf1cae01dfaea29f5483a75 upstream. The command ring and cursor ring use different notify port addresses definition: QXL_IO_NOTIFY_CMD and QXL_IO_NOTIFY_CURSOR. However, in qxl_device_init() we use QXL_IO_NOTIFY_CMD to create both command ring and cursor ring. This doesn't cause any problems now, because QEMU's behaviors on QXL_IO_NOTIFY_CMD and QXL_IO_NOTIFY_CURSOR are the same. However, QEMU's behavior may be change in future, so let's fix it. P.S.: In the X.org QXL driver, the notify port address of cursor ring is correct. Signed-off-by: Huacai Chen Cc: Link: http://patchwork.freedesktop.org/patch/msgid/1585635488-17507-1-git-send-email-chenhc@lemote.com Signed-off-by: Gerd Hoffmann Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/qxl/qxl_kms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c index c5716a0ca3b8..20ca0a75e685 100644 --- a/drivers/gpu/drm/qxl/qxl_kms.c +++ b/drivers/gpu/drm/qxl/qxl_kms.c @@ -181,7 +181,7 @@ int qxl_device_init(struct qxl_device *qdev, &(qdev->ram_header->cursor_ring_hdr), sizeof(struct qxl_command), QXL_CURSOR_RING_SIZE, - qdev->io_base + QXL_IO_NOTIFY_CMD, + qdev->io_base + QXL_IO_NOTIFY_CURSOR, false, &qdev->cursor_event); From 808db35a0acf5381691a96439c86f05a2c72ebe8 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 10 Jun 2020 14:57:13 -0700 Subject: [PATCH 135/162] selinux: fix double free commit 65de50969a77509452ae590e9449b70a22b923bb upstream. Clang's static analysis tool reports these double free memory errors. security/selinux/ss/services.c:2987:4: warning: Attempt to free released memory [unix.Malloc] kfree(bnames[i]); ^~~~~~~~~~~~~~~~ security/selinux/ss/services.c:2990:2: warning: Attempt to free released memory [unix.Malloc] kfree(bvalues); ^~~~~~~~~~~~~~ So improve the security_get_bools error handling by freeing these variables and setting their return pointers to NULL and the return len to 0 Cc: stable@vger.kernel.org Signed-off-by: Tom Rix Acked-by: Stephen Smalley Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- security/selinux/ss/services.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index b275743e23cc..0158cde957ee 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -2736,8 +2736,12 @@ err: if (*names) { for (i = 0; i < *len; i++) kfree((*names)[i]); + kfree(*names); } kfree(*values); + *len = 0; + *names = NULL; + *values = NULL; goto out; } From c749941b90de6cb4c6b6fd286d0105c69d78ce14 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Fri, 22 May 2020 12:18:44 +0800 Subject: [PATCH 136/162] ext4: fix partial cluster initialization when splitting extent [ Upstream commit cfb3c85a600c6aa25a2581b3c1c4db3460f14e46 ] Fix the bug when calculating the physical block number of the first block in the split extent. This bug will cause xfstests shared/298 failure on ext4 with bigalloc enabled occasionally. Ext4 error messages indicate that previously freed blocks are being freed again, and the following fsck will fail due to the inconsistency of block bitmap and bg descriptor. The following is an example case: 1. First, Initialize a ext4 filesystem with cluster size '16K', block size '4K', in which case, one cluster contains four blocks. 2. Create one file (e.g., xxx.img) on this ext4 filesystem. Now the extent tree of this file is like: ... 36864:[0]4:220160 36868:[0]14332:145408 51200:[0]2:231424 ... 3. Then execute PUNCH_HOLE fallocate on this file. The hole range is like: .. ext4_ext_remove_space: dev 254,16 ino 12 since 49506 end 49506 depth 1 ext4_ext_remove_space: dev 254,16 ino 12 since 49544 end 49546 depth 1 ext4_ext_remove_space: dev 254,16 ino 12 since 49605 end 49607 depth 1 ... 4. Then the extent tree of this file after punching is like ... 49507:[0]37:158047 49547:[0]58:158087 ... 5. Detailed procedure of punching hole [49544, 49546] 5.1. The block address space: ``` lblk ~49505 49506 49507~49543 49544~49546 49547~ ---------+------+-------------+----------------+-------- extent | hole | extent | hole | extent ---------+------+-------------+----------------+-------- pblk ~158045 158046 158047~158083 158084~158086 158087~ ``` 5.2. The detailed layout of cluster 39521: ``` cluster 39521 <-------------------------------> hole extent <----------------------><-------- lblk 49544 49545 49546 49547 +-------+-------+-------+-------+ | | | | | +-------+-------+-------+-------+ pblk 158084 1580845 158086 158087 ``` 5.3. The ftrace output when punching hole [49544, 49546]: - ext4_ext_remove_space (start 49544, end 49546) - ext4_ext_rm_leaf (start 49544, end 49546, last_extent [49507(158047), 40], partial [pclu 39522 lblk 0 state 2]) - ext4_remove_blocks (extent [49507(158047), 40], from 49544 to 49546, partial [pclu 39522 lblk 0 state 2] - ext4_free_blocks: (block 158084 count 4) - ext4_mballoc_free (extent 1/6753/1) 5.4. Ext4 error message in dmesg: EXT4-fs error (device vdb): mb_free_blocks:1457: group 1, block 158084:freeing already freed block (bit 6753); block bitmap corrupt. EXT4-fs error (device vdb): ext4_mb_generate_buddy:747: group 1, block bitmap and bg descriptor inconsistent: 19550 vs 19551 free clusters In this case, the whole cluster 39521 is freed mistakenly when freeing pblock 158084~158086 (i.e., the first three blocks of this cluster), although pblock 158087 (the last remaining block of this cluster) has not been freed yet. The root cause of this isuue is that, the pclu of the partial cluster is calculated mistakenly in ext4_ext_remove_space(). The correct partial_cluster.pclu (i.e., the cluster number of the first block in the next extent, that is, lblock 49597 (pblock 158086)) should be 39521 rather than 39522. Fixes: f4226d9ea400 ("ext4: fix partial cluster initialization") Signed-off-by: Jeffle Xu Reviewed-by: Eric Whitney Cc: stable@kernel.org # v3.19+ Link: https://lore.kernel.org/r/1590121124-37096-1-git-send-email-jefflexu@linux.alibaba.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/extents.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4f9eb4b61549..fc6bc261f7ac 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2917,7 +2917,7 @@ again: * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { - pblk = ext4_ext_pblock(ex) + end - ee_block + 2; + pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial_cluster = -(long long) EXT4_B2C(sbi, pblk); } From 75e8b93aad2a3e1efa311f7979fe5b163190bff8 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Fri, 3 Apr 2020 15:47:15 -0400 Subject: [PATCH 137/162] drm/dp_mst: Increase ACT retry timeout to 3s MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 873a95e0d59ac06901ae261dda0b7165ffd002b8 ] Currently we only poll for an ACT up to 30 times, with a busy-wait delay of 100µs between each attempt - giving us a timeout of 2900µs. While this might seem sensible, it would appear that in certain scenarios it can take dramatically longer then that for us to receive an ACT. On one of the EVGA MST hubs that I have available, I observed said hub sometimes taking longer then a second before signalling the ACT. These delays mostly seem to occur when previous sideband messages we've sent are NAKd by the hub, however it wouldn't be particularly surprising if it's possible to reproduce times like this simply by introducing branch devices with large LCTs since payload allocations have to take effect on every downstream device up to the payload's target. So, instead of just retrying 30 times we poll for the ACT for up to 3ms, and additionally use usleep_range() to avoid a very long and rude busy-wait. Note that the previous retry count of 30 appears to have been arbitrarily chosen, as I can't find any mention of a recommended timeout or retry count for ACTs in the DisplayPort 2.0 specification. This also goes for the range we were previously using for udelay(), although I suspect that was just copied from the recommended delay for link training on SST devices. Changes since v1: * Use readx_poll_timeout() instead of open-coding timeout loop - Sean Paul Changes since v2: * Increase poll interval to 200us - Sean Paul * Print status in hex when we timeout waiting for ACT - Sean Paul Signed-off-by: Lyude Paul Fixes: ad7f8a1f9ced ("drm/helper: add Displayport multi-stream helper (v0.6)") Cc: Sean Paul Cc: # v3.17+ Reviewed-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200406221253.1307209-4-lyude@redhat.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_dp_mst_topology.c | 52 ++++++++++++++++----------- 1 file changed, 31 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index df5d853f96ee..e52381c9d04e 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -2751,6 +2752,17 @@ fail: return ret; } +static int do_get_act_status(struct drm_dp_aux *aux) +{ + int ret; + u8 status; + + ret = drm_dp_dpcd_readb(aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status); + if (ret < 0) + return ret; + + return status; +} /** * drm_dp_check_act_status() - Check ACT handled status. @@ -2760,30 +2772,28 @@ fail: */ int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr) { - int count = 0, ret; - u8 status; + /* + * There doesn't seem to be any recommended retry count or timeout in + * the MST specification. Since some hubs have been observed to take + * over 1 second to update their payload allocations under certain + * conditions, we use a rather large timeout value. + */ + const int timeout_ms = 3000; + int ret, status; - do { - ret = drm_dp_dpcd_readb(mgr->aux, - DP_PAYLOAD_TABLE_UPDATE_STATUS, - &status); - if (ret < 0) { - DRM_DEBUG_KMS("failed to read payload table status %d\n", - ret); - return ret; - } - - if (status & DP_PAYLOAD_ACT_HANDLED) - break; - count++; - udelay(100); - } while (count < 30); - - if (!(status & DP_PAYLOAD_ACT_HANDLED)) { - DRM_DEBUG_KMS("failed to get ACT bit %d after %d retries\n", - status, count); + ret = readx_poll_timeout(do_get_act_status, mgr->aux, status, + status & DP_PAYLOAD_ACT_HANDLED || status < 0, + 200, timeout_ms * USEC_PER_MSEC); + if (ret < 0 && status >= 0) { + DRM_DEBUG_KMS("Failed to get ACT after %dms, last status: %02x\n", + timeout_ms, status); return -EINVAL; + } else if (status < 0) { + DRM_DEBUG_KMS("Failed to read payload table status: %d\n", + status); + return status; } + return 0; } EXPORT_SYMBOL(drm_dp_check_act_status); From acc943f56efe460b5e6ff78b92844f63a4078eb6 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 22 Jun 2020 19:56:39 +0000 Subject: [PATCH 138/162] x86/boot/compressed: Relax sed symbol type regex for LLVM ld.lld commit bc310baf2ba381c648983c7f4748327f17324562 upstream. The final build stage of the x86 kernel captures some symbol addresses from the decompressor binary and copies them into zoffset.h. It uses sed with a regular expression that matches the address, symbol type and symbol name, and mangles the captured addresses and the names of symbols of interest into #define directives that are added to zoffset.h The symbol type is indicated by a single letter, which we match strictly: only letters in the set 'ABCDGRSTVW' are matched, even though the actual symbol type is relevant and therefore ignored. Commit bc7c9d620 ("efi/libstub/x86: Force 'hidden' visibility for extern declarations") made a change to the way external symbol references are classified, resulting in 'startup_32' now being emitted as a hidden symbol. This prevents the use of GOT entries to refer to this symbol via its absolute address, which recent toolchains (including Clang based ones) already avoid by default, making this change a no-op in the majority of cases. However, as it turns out, the LLVM linker classifies such hidden symbols as symbols with static linkage in fully linked ELF binaries, causing tools such as NM to output a lowercase 't' rather than an upper case 'T' for the type of such symbols. Since our sed expression only matches upper case letters for the symbol type, the line describing startup_32 is disregarded, resulting in a build error like the following arch/x86/boot/header.S:568:18: error: symbol 'ZO_startup_32' can not be undefined in a subtraction expression init_size: .long (0x00000000008fd000 - ZO_startup_32 + (((0x0000000001f6361c + ((0x0000000001f6361c >> 8) + 65536) - 0x00000000008c32e5) + 4095) & ~4095)) # kernel initialization size Given that we are only interested in the value of the symbol, let's match any character in the set 'a-zA-Z' instead. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Tested-by: Nathan Chancellor Signed-off-by: Nathan Chancellor Signed-off-by: Sasha Levin --- arch/x86/boot/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 1c060748c813..f38ffcc610d2 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -87,7 +87,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ From 5bc796dcac257ebc2cdb601b978b7ff7e1f19e01 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Wed, 3 Jun 2020 16:49:48 +0200 Subject: [PATCH 139/162] block: nr_sects_write(): Disable preemption on seqcount write [ Upstream commit 15b81ce5abdc4b502aa31dff2d415b79d2349d2f ] For optimized block readers not holding a mutex, the "number of sectors" 64-bit value is protected from tearing on 32-bit architectures by a sequence counter. Disable preemption before entering that sequence counter's write side critical section. Otherwise, the read side can preempt the write side section and spin for the entire scheduler tick. If the reader belongs to a real-time scheduling class, it can spin forever and the kernel will livelock. Fixes: c83f6bf98dc1 ("block: add partition resize function to blkpg ioctl") Cc: Signed-off-by: Ahmed S. Darwish Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- include/linux/genhd.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 550fa358893a..37f30d62f3a2 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -693,9 +693,11 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part) static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) { #if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP) + preempt_disable(); write_seqcount_begin(&part->nr_sects_seq); part->nr_sects = size; write_seqcount_end(&part->nr_sects_seq); + preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT) preempt_disable(); part->nr_sects = size; From 5bcfcbfc40192e8198d9d3997f2f15c5a5c964b2 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:15 +0200 Subject: [PATCH 140/162] mtd: rawnand: Pass a nand_chip object to nand_release() [ Upstream commit 59ac276f22270fb2094910f9a734c17f41c25e70 ] Let's make the raw NAND API consistent by patching all helpers to take a nand_chip object instead of an mtd_info one. Now is nand_release()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal Signed-off-by: Sasha Levin --- Documentation/driver-api/mtdnand.rst | 2 +- drivers/mtd/nand/ams-delta.c | 2 +- drivers/mtd/nand/au1550nd.c | 2 +- drivers/mtd/nand/bcm47xxnflash/main.c | 2 +- drivers/mtd/nand/bf5xx_nand.c | 2 +- drivers/mtd/nand/brcmnand/brcmnand.c | 2 +- drivers/mtd/nand/cafe_nand.c | 2 +- drivers/mtd/nand/cmx270_nand.c | 2 +- drivers/mtd/nand/cs553x_nand.c | 2 +- drivers/mtd/nand/davinci_nand.c | 2 +- drivers/mtd/nand/denali.c | 4 +--- drivers/mtd/nand/diskonchip.c | 4 ++-- drivers/mtd/nand/docg4.c | 4 ++-- drivers/mtd/nand/fsl_elbc_nand.c | 2 +- drivers/mtd/nand/fsl_ifc_nand.c | 2 +- drivers/mtd/nand/fsl_upm.c | 2 +- drivers/mtd/nand/fsmc_nand.c | 2 +- drivers/mtd/nand/gpio.c | 2 +- drivers/mtd/nand/gpmi-nand/gpmi-nand.c | 2 +- drivers/mtd/nand/hisi504_nand.c | 5 ++--- drivers/mtd/nand/jz4740_nand.c | 4 ++-- drivers/mtd/nand/jz4780_nand.c | 4 ++-- drivers/mtd/nand/lpc32xx_mlc.c | 5 ++--- drivers/mtd/nand/lpc32xx_slc.c | 5 ++--- drivers/mtd/nand/mpc5121_nfc.c | 2 +- drivers/mtd/nand/mtk_nand.c | 4 ++-- drivers/mtd/nand/mxc_nand.c | 2 +- drivers/mtd/nand/nand_base.c | 8 ++++---- drivers/mtd/nand/nandsim.c | 4 ++-- drivers/mtd/nand/ndfc.c | 2 +- drivers/mtd/nand/nuc900_nand.c | 2 +- drivers/mtd/nand/omap2.c | 2 +- drivers/mtd/nand/orion_nand.c | 5 ++--- drivers/mtd/nand/oxnas_nand.c | 4 ++-- drivers/mtd/nand/pasemi_nand.c | 2 +- drivers/mtd/nand/plat_nand.c | 4 ++-- drivers/mtd/nand/pxa3xx_nand.c | 2 +- drivers/mtd/nand/qcom_nandc.c | 2 +- drivers/mtd/nand/r852.c | 4 ++-- drivers/mtd/nand/s3c2410.c | 2 +- drivers/mtd/nand/sh_flctl.c | 2 +- drivers/mtd/nand/sharpsl.c | 4 ++-- drivers/mtd/nand/socrates_nand.c | 5 ++--- drivers/mtd/nand/sunxi_nand.c | 4 ++-- drivers/mtd/nand/tango_nand.c | 2 +- drivers/mtd/nand/tmio_nand.c | 4 ++-- drivers/mtd/nand/txx9ndfmc.c | 2 +- drivers/mtd/nand/vf610_nfc.c | 2 +- drivers/mtd/nand/xway_nand.c | 4 ++-- include/linux/mtd/rawnand.h | 6 ++---- 50 files changed, 72 insertions(+), 81 deletions(-) diff --git a/Documentation/driver-api/mtdnand.rst b/Documentation/driver-api/mtdnand.rst index 2a5191b6d445..15449334b124 100644 --- a/Documentation/driver-api/mtdnand.rst +++ b/Documentation/driver-api/mtdnand.rst @@ -277,7 +277,7 @@ unregisters the partitions in the MTD layer. static void __exit board_cleanup (void) { /* Release resources, unregister device */ - nand_release (board_mtd); + nand_release (mtd_to_nand(board_mtd)); /* unmap physical address */ iounmap(baseaddr); diff --git a/drivers/mtd/nand/ams-delta.c b/drivers/mtd/nand/ams-delta.c index dcec9cf4983f..e22a9ffa9cb7 100644 --- a/drivers/mtd/nand/ams-delta.c +++ b/drivers/mtd/nand/ams-delta.c @@ -263,7 +263,7 @@ static int ams_delta_cleanup(struct platform_device *pdev) void __iomem *io_base = platform_get_drvdata(pdev); /* Release resources, unregister device */ - nand_release(ams_delta_mtd); + nand_release(mtd_to_nand(ams_delta_mtd)); gpio_free_array(_mandatory_gpio, ARRAY_SIZE(_mandatory_gpio)); gpio_free(AMS_DELTA_GPIO_PIN_NAND_RB); diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c index 9d4a28fa6b73..99c738be2545 100644 --- a/drivers/mtd/nand/au1550nd.c +++ b/drivers/mtd/nand/au1550nd.c @@ -496,7 +496,7 @@ static int au1550nd_remove(struct platform_device *pdev) struct au1550nd_ctx *ctx = platform_get_drvdata(pdev); struct resource *r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - nand_release(nand_to_mtd(&ctx->chip)); + nand_release(&ctx->chip); iounmap(ctx->base); release_mem_region(r->start, 0x1000); kfree(ctx); diff --git a/drivers/mtd/nand/bcm47xxnflash/main.c b/drivers/mtd/nand/bcm47xxnflash/main.c index fb31429b70a9..d79694160845 100644 --- a/drivers/mtd/nand/bcm47xxnflash/main.c +++ b/drivers/mtd/nand/bcm47xxnflash/main.c @@ -65,7 +65,7 @@ static int bcm47xxnflash_remove(struct platform_device *pdev) { struct bcm47xxnflash *nflash = platform_get_drvdata(pdev); - nand_release(nand_to_mtd(&nflash->nand_chip)); + nand_release(&nflash->nand_chip); return 0; } diff --git a/drivers/mtd/nand/bf5xx_nand.c b/drivers/mtd/nand/bf5xx_nand.c index 5655dca6ce43..ebcbcbaa8b54 100644 --- a/drivers/mtd/nand/bf5xx_nand.c +++ b/drivers/mtd/nand/bf5xx_nand.c @@ -688,7 +688,7 @@ static int bf5xx_nand_remove(struct platform_device *pdev) * and their partitions, then go through freeing the * resources used */ - nand_release(nand_to_mtd(&info->chip)); + nand_release(&info->chip); peripheral_free_list(bfin_nfc_pin_req); bf5xx_nand_dma_remove(info); diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c index f8d793b15a7a..2bb8e6faa539 100644 --- a/drivers/mtd/nand/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/brcmnand/brcmnand.c @@ -2597,7 +2597,7 @@ int brcmnand_remove(struct platform_device *pdev) struct brcmnand_host *host; list_for_each_entry(host, &ctrl->host_list, node) - nand_release(nand_to_mtd(&host->chip)); + nand_release(&host->chip); clk_disable_unprepare(ctrl->clk); diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c index bc558c438a57..98c013094fa2 100644 --- a/drivers/mtd/nand/cafe_nand.c +++ b/drivers/mtd/nand/cafe_nand.c @@ -826,7 +826,7 @@ static void cafe_nand_remove(struct pci_dev *pdev) /* Disable NAND IRQ in global IRQ mask register */ cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK); free_irq(pdev->irq, mtd); - nand_release(mtd); + nand_release(chip); free_rs(cafe->rs); pci_iounmap(pdev, cafe->mmio); dma_free_coherent(&cafe->pdev->dev, diff --git a/drivers/mtd/nand/cmx270_nand.c b/drivers/mtd/nand/cmx270_nand.c index 1fc435f994e1..7b824ae88ab0 100644 --- a/drivers/mtd/nand/cmx270_nand.c +++ b/drivers/mtd/nand/cmx270_nand.c @@ -230,7 +230,7 @@ module_init(cmx270_init); static void __exit cmx270_cleanup(void) { /* Release resources, unregister device */ - nand_release(cmx270_nand_mtd); + nand_release(mtd_to_nand(cmx270_nand_mtd)); gpio_free(GPIO_NAND_RB); gpio_free(GPIO_NAND_CS); diff --git a/drivers/mtd/nand/cs553x_nand.c b/drivers/mtd/nand/cs553x_nand.c index d48877540f14..647d4ee69345 100644 --- a/drivers/mtd/nand/cs553x_nand.c +++ b/drivers/mtd/nand/cs553x_nand.c @@ -338,7 +338,7 @@ static void __exit cs553x_cleanup(void) mmio_base = this->IO_ADDR_R; /* Release resources, unregister device */ - nand_release(mtd); + nand_release(this); kfree(mtd->name); cs553x_mtd[i] = NULL; diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c index ccc8c43abcff..e66f1385b49e 100644 --- a/drivers/mtd/nand/davinci_nand.c +++ b/drivers/mtd/nand/davinci_nand.c @@ -854,7 +854,7 @@ static int nand_davinci_remove(struct platform_device *pdev) ecc4_busy = false; spin_unlock_irq(&davinci_nand_lock); - nand_release(nand_to_mtd(&info->chip)); + nand_release(&info->chip); clk_disable_unprepare(info->clk); diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 3087b0ba7b7f..390a18ad68ee 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -1444,9 +1444,7 @@ EXPORT_SYMBOL(denali_init); /* driver exit point */ void denali_remove(struct denali_nand_info *denali) { - struct mtd_info *mtd = nand_to_mtd(&denali->nand); - - nand_release(mtd); + nand_release(&denali->nand); kfree(denali->buf); denali_disable_irq(denali); } diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c index c3aa53caab5c..12cac07f5cf2 100644 --- a/drivers/mtd/nand/diskonchip.c +++ b/drivers/mtd/nand/diskonchip.c @@ -1611,7 +1611,7 @@ static int __init doc_probe(unsigned long physadr) /* nand_release will call mtd_device_unregister, but we haven't yet added it. This is handled without incident by mtd_device_unregister, as far as I can tell. */ - nand_release(mtd); + nand_release(nand); kfree(nand); goto fail; } @@ -1644,7 +1644,7 @@ static void release_nanddoc(void) doc = nand_get_controller_data(nand); nextmtd = doc->nextdoc; - nand_release(mtd); + nand_release(nand); iounmap(doc->virtadr); release_mem_region(doc->physadr, DOC_IOREMAP_LEN); kfree(nand); diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c index 2436cbc71662..53fdf491d8c0 100644 --- a/drivers/mtd/nand/docg4.c +++ b/drivers/mtd/nand/docg4.c @@ -1376,7 +1376,7 @@ static int __init probe_docg4(struct platform_device *pdev) return 0; fail: - nand_release(mtd); /* deletes partitions and mtd devices */ + nand_release(nand); /* deletes partitions and mtd devices */ free_bch(doc->bch); kfree(nand); @@ -1389,7 +1389,7 @@ fail_unmap: static int __exit cleanup_docg4(struct platform_device *pdev) { struct docg4_priv *doc = platform_get_drvdata(pdev); - nand_release(doc->mtd); + nand_release(mtd_to_nand(doc->mtd)); free_bch(doc->bch); kfree(mtd_to_nand(doc->mtd)); iounmap(doc->virtadr); diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c index 17db2f90aa2c..0f70bd961234 100644 --- a/drivers/mtd/nand/fsl_elbc_nand.c +++ b/drivers/mtd/nand/fsl_elbc_nand.c @@ -813,7 +813,7 @@ static int fsl_elbc_chip_remove(struct fsl_elbc_mtd *priv) struct fsl_elbc_fcm_ctrl *elbc_fcm_ctrl = priv->ctrl->nand; struct mtd_info *mtd = nand_to_mtd(&priv->chip); - nand_release(mtd); + nand_release(&priv->chip); kfree(mtd->name); diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c index 16deba1a2385..0d4928161439 100644 --- a/drivers/mtd/nand/fsl_ifc_nand.c +++ b/drivers/mtd/nand/fsl_ifc_nand.c @@ -927,7 +927,7 @@ static int fsl_ifc_chip_remove(struct fsl_ifc_mtd *priv) { struct mtd_info *mtd = nand_to_mtd(&priv->chip); - nand_release(mtd); + nand_release(&priv->chip); kfree(mtd->name); diff --git a/drivers/mtd/nand/fsl_upm.c b/drivers/mtd/nand/fsl_upm.c index a88e2cf66e0f..009e96fb92ae 100644 --- a/drivers/mtd/nand/fsl_upm.c +++ b/drivers/mtd/nand/fsl_upm.c @@ -326,7 +326,7 @@ static int fun_remove(struct platform_device *ofdev) struct mtd_info *mtd = nand_to_mtd(&fun->chip); int i; - nand_release(mtd); + nand_release(&fun->chip); kfree(mtd->name); for (i = 0; i < fun->mchip_count; i++) { diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index eac15d9bf49e..3be80e15e400 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -1118,7 +1118,7 @@ static int fsmc_nand_remove(struct platform_device *pdev) struct fsmc_nand_data *host = platform_get_drvdata(pdev); if (host) { - nand_release(nand_to_mtd(&host->nand)); + nand_release(&host->nand); if (host->mode == USE_DMA_ACCESS) { dma_release_channel(host->write_dma_chan); diff --git a/drivers/mtd/nand/gpio.c b/drivers/mtd/nand/gpio.c index fd3648952b5a..81b02b81e984 100644 --- a/drivers/mtd/nand/gpio.c +++ b/drivers/mtd/nand/gpio.c @@ -199,7 +199,7 @@ static int gpio_nand_remove(struct platform_device *pdev) { struct gpiomtd *gpiomtd = platform_get_drvdata(pdev); - nand_release(nand_to_mtd(&gpiomtd->nand_chip)); + nand_release(&gpiomtd->nand_chip); if (gpio_is_valid(gpiomtd->plat.gpio_nwp)) gpio_set_value(gpiomtd->plat.gpio_nwp, 0); diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index d4d824ef64e9..c7d0d2eed6c2 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -2135,7 +2135,7 @@ static int gpmi_nand_remove(struct platform_device *pdev) { struct gpmi_nand_data *this = platform_get_drvdata(pdev); - nand_release(nand_to_mtd(&this->nand)); + nand_release(&this->nand); gpmi_free_dma_buffer(this); release_resources(this); return 0; diff --git a/drivers/mtd/nand/hisi504_nand.c b/drivers/mtd/nand/hisi504_nand.c index d9ee1a7e6956..1d1b541489f8 100644 --- a/drivers/mtd/nand/hisi504_nand.c +++ b/drivers/mtd/nand/hisi504_nand.c @@ -823,7 +823,7 @@ static int hisi_nfc_probe(struct platform_device *pdev) return 0; err_mtd: - nand_release(mtd); + nand_release(chip); err_res: return ret; } @@ -831,9 +831,8 @@ err_res: static int hisi_nfc_remove(struct platform_device *pdev) { struct hinfc_host *host = platform_get_drvdata(pdev); - struct mtd_info *mtd = nand_to_mtd(&host->chip); - nand_release(mtd); + nand_release(&host->chip); return 0; } diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c index ad827d4af3e9..62ddea88edce 100644 --- a/drivers/mtd/nand/jz4740_nand.c +++ b/drivers/mtd/nand/jz4740_nand.c @@ -480,7 +480,7 @@ static int jz_nand_probe(struct platform_device *pdev) return 0; err_nand_release: - nand_release(mtd); + nand_release(chip); err_unclaim_banks: while (chipnr--) { unsigned char bank = nand->banks[chipnr]; @@ -500,7 +500,7 @@ static int jz_nand_remove(struct platform_device *pdev) struct jz_nand *nand = platform_get_drvdata(pdev); size_t i; - nand_release(nand_to_mtd(&nand->chip)); + nand_release(&nand->chip); /* Deassert and disable all chips */ writel(0, nand->base + JZ_REG_NAND_CTRL); diff --git a/drivers/mtd/nand/jz4780_nand.c b/drivers/mtd/nand/jz4780_nand.c index e69f6ae4c539..86ff46eb7925 100644 --- a/drivers/mtd/nand/jz4780_nand.c +++ b/drivers/mtd/nand/jz4780_nand.c @@ -293,7 +293,7 @@ static int jz4780_nand_init_chip(struct platform_device *pdev, ret = mtd_device_register(mtd, NULL, 0); if (ret) { - nand_release(mtd); + nand_release(chip); return ret; } @@ -308,7 +308,7 @@ static void jz4780_nand_cleanup_chips(struct jz4780_nand_controller *nfc) while (!list_empty(&nfc->chips)) { chip = list_first_entry(&nfc->chips, struct jz4780_nand_chip, chip_list); - nand_release(nand_to_mtd(&chip->chip)); + nand_release(&chip->chip); list_del(&chip->chip_list); } } diff --git a/drivers/mtd/nand/lpc32xx_mlc.c b/drivers/mtd/nand/lpc32xx_mlc.c index 5796468db653..d19d07931c2b 100644 --- a/drivers/mtd/nand/lpc32xx_mlc.c +++ b/drivers/mtd/nand/lpc32xx_mlc.c @@ -805,7 +805,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) if (!res) return res; - nand_release(mtd); + nand_release(nand_chip); err_exit4: free_irq(host->irq, host); @@ -829,9 +829,8 @@ err_exit1: static int lpc32xx_nand_remove(struct platform_device *pdev) { struct lpc32xx_nand_host *host = platform_get_drvdata(pdev); - struct mtd_info *mtd = nand_to_mtd(&host->nand_chip); - nand_release(mtd); + nand_release(&host->nand_chip); free_irq(host->irq, host); if (use_dma) dma_release_channel(host->dma_chan); diff --git a/drivers/mtd/nand/lpc32xx_slc.c b/drivers/mtd/nand/lpc32xx_slc.c index b61f28a1554d..1be4aaa3d6e0 100644 --- a/drivers/mtd/nand/lpc32xx_slc.c +++ b/drivers/mtd/nand/lpc32xx_slc.c @@ -935,7 +935,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) if (!res) return res; - nand_release(mtd); + nand_release(chip); err_exit3: dma_release_channel(host->dma_chan); @@ -954,9 +954,8 @@ static int lpc32xx_nand_remove(struct platform_device *pdev) { uint32_t tmp; struct lpc32xx_nand_host *host = platform_get_drvdata(pdev); - struct mtd_info *mtd = nand_to_mtd(&host->nand_chip); - nand_release(mtd); + nand_release(&host->nand_chip); dma_release_channel(host->dma_chan); /* Force CE high */ diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c index b6b97cc9fba6..b8a93b47a290 100644 --- a/drivers/mtd/nand/mpc5121_nfc.c +++ b/drivers/mtd/nand/mpc5121_nfc.c @@ -829,7 +829,7 @@ static int mpc5121_nfc_remove(struct platform_device *op) struct device *dev = &op->dev; struct mtd_info *mtd = dev_get_drvdata(dev); - nand_release(mtd); + nand_release(mtd_to_nand(mtd)); mpc5121_nfc_free(dev, mtd); return 0; diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index e17f838b9b81..27fcce71ad38 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -1357,7 +1357,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc, ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0); if (ret) { dev_err(dev, "mtd parse partition error\n"); - nand_release(mtd); + nand_release(nand); return ret; } @@ -1514,7 +1514,7 @@ static int mtk_nfc_remove(struct platform_device *pdev) while (!list_empty(&nfc->chips)) { chip = list_first_entry(&nfc->chips, struct mtk_nfc_nand_chip, node); - nand_release(nand_to_mtd(&chip->nand)); + nand_release(&chip->nand); list_del(&chip->node); } diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c index fcb575d55b89..808d85bde9f2 100644 --- a/drivers/mtd/nand/mxc_nand.c +++ b/drivers/mtd/nand/mxc_nand.c @@ -1834,7 +1834,7 @@ static int mxcnd_remove(struct platform_device *pdev) { struct mxc_nand_host *host = platform_get_drvdata(pdev); - nand_release(nand_to_mtd(&host->nand)); + nand_release(&host->nand); if (host->clk_act) clk_disable_unprepare(host->clk); diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index d410de331854..e953eca67608 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -5046,12 +5046,12 @@ EXPORT_SYMBOL_GPL(nand_cleanup); /** * nand_release - [NAND Interface] Unregister the MTD device and free resources * held by the NAND device - * @mtd: MTD device structure + * @chip: NAND chip object */ -void nand_release(struct mtd_info *mtd) +void nand_release(struct nand_chip *chip) { - mtd_device_unregister(mtd); - nand_cleanup(mtd_to_nand(mtd)); + mtd_device_unregister(nand_to_mtd(chip)); + nand_cleanup(chip); } EXPORT_SYMBOL_GPL(nand_release); diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c index 44322a363ba5..dbb0e47f5197 100644 --- a/drivers/mtd/nand/nandsim.c +++ b/drivers/mtd/nand/nandsim.c @@ -2356,7 +2356,7 @@ static int __init ns_init_module(void) err_exit: free_nandsim(nand); - nand_release(nsmtd); + nand_release(chip); for (i = 0;i < ARRAY_SIZE(nand->partitions); ++i) kfree(nand->partitions[i].name); error: @@ -2378,7 +2378,7 @@ static void __exit ns_cleanup_module(void) int i; free_nandsim(ns); /* Free nandsim private resources */ - nand_release(nsmtd); /* Unregister driver */ + nand_release(chip); /* Unregister driver */ for (i = 0;i < ARRAY_SIZE(ns->partitions); ++i) kfree(ns->partitions[i].name); kfree(mtd_to_nand(nsmtd)); /* Free other structures */ diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c index d8a806894937..eb84328d9bde 100644 --- a/drivers/mtd/nand/ndfc.c +++ b/drivers/mtd/nand/ndfc.c @@ -258,7 +258,7 @@ static int ndfc_remove(struct platform_device *ofdev) struct ndfc_controller *ndfc = dev_get_drvdata(&ofdev->dev); struct mtd_info *mtd = nand_to_mtd(&ndfc->chip); - nand_release(mtd); + nand_release(&ndfc->chip); kfree(mtd->name); return 0; diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c index 7bb4d2ea9342..a79f88c6d010 100644 --- a/drivers/mtd/nand/nuc900_nand.c +++ b/drivers/mtd/nand/nuc900_nand.c @@ -284,7 +284,7 @@ static int nuc900_nand_remove(struct platform_device *pdev) { struct nuc900_nand *nuc900_nand = platform_get_drvdata(pdev); - nand_release(nand_to_mtd(&nuc900_nand->chip)); + nand_release(&nuc900_nand->chip); clk_disable(nuc900_nand->clk); return 0; diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index 9f98f74ff221..110c0726c665 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -2306,7 +2306,7 @@ static int omap_nand_remove(struct platform_device *pdev) } if (info->dma) dma_release_channel(info->dma); - nand_release(mtd); + nand_release(nand_chip); return 0; } diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c index 5a5aa1f07d07..2f21c678d6ef 100644 --- a/drivers/mtd/nand/orion_nand.c +++ b/drivers/mtd/nand/orion_nand.c @@ -186,7 +186,7 @@ static int __init orion_nand_probe(struct platform_device *pdev) mtd->name = "orion_nand"; ret = mtd_device_register(mtd, board->parts, board->nr_parts); if (ret) { - nand_release(mtd); + nand_release(nc); goto no_dev; } @@ -201,9 +201,8 @@ static int orion_nand_remove(struct platform_device *pdev) { struct orion_nand_info *info = platform_get_drvdata(pdev); struct nand_chip *chip = &info->chip; - struct mtd_info *mtd = nand_to_mtd(chip); - nand_release(mtd); + nand_release(chip); clk_disable_unprepare(info->clk); diff --git a/drivers/mtd/nand/oxnas_nand.c b/drivers/mtd/nand/oxnas_nand.c index d649d5944826..ff5899988738 100644 --- a/drivers/mtd/nand/oxnas_nand.c +++ b/drivers/mtd/nand/oxnas_nand.c @@ -148,7 +148,7 @@ static int oxnas_nand_probe(struct platform_device *pdev) err = mtd_device_register(mtd, NULL, 0); if (err) { - nand_release(mtd); + nand_release(chip); goto err_clk_unprepare; } @@ -176,7 +176,7 @@ static int oxnas_nand_remove(struct platform_device *pdev) struct oxnas_nand_ctrl *oxnas = platform_get_drvdata(pdev); if (oxnas->chips[0]) - nand_release(nand_to_mtd(oxnas->chips[0])); + nand_release(oxnas->chips[0]); clk_disable_unprepare(oxnas->clk); diff --git a/drivers/mtd/nand/pasemi_nand.c b/drivers/mtd/nand/pasemi_nand.c index d69e5bae541e..f0f4ff960965 100644 --- a/drivers/mtd/nand/pasemi_nand.c +++ b/drivers/mtd/nand/pasemi_nand.c @@ -193,7 +193,7 @@ static int pasemi_nand_remove(struct platform_device *ofdev) chip = mtd_to_nand(pasemi_nand_mtd); /* Release resources, unregister device */ - nand_release(pasemi_nand_mtd); + nand_release(chip); release_region(lpcctl, 4); diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c index 925a1323604d..2906996d2262 100644 --- a/drivers/mtd/nand/plat_nand.c +++ b/drivers/mtd/nand/plat_nand.c @@ -99,7 +99,7 @@ static int plat_nand_probe(struct platform_device *pdev) if (!err) return err; - nand_release(mtd); + nand_release(&data->chip); out: if (pdata->ctrl.remove) pdata->ctrl.remove(pdev); @@ -114,7 +114,7 @@ static int plat_nand_remove(struct platform_device *pdev) struct plat_nand_data *data = platform_get_drvdata(pdev); struct platform_nand_data *pdata = dev_get_platdata(&pdev->dev); - nand_release(nand_to_mtd(&data->chip)); + nand_release(&data->chip); if (pdata->ctrl.remove) pdata->ctrl.remove(pdev); diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 125b744c9c28..df62f99979f3 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -1915,7 +1915,7 @@ static int pxa3xx_nand_remove(struct platform_device *pdev) clk_disable_unprepare(info->clk); for (cs = 0; cs < pdata->num_cs; cs++) - nand_release(nand_to_mtd(&info->host[cs]->chip)); + nand_release(&info->host[cs]->chip); return 0; } diff --git a/drivers/mtd/nand/qcom_nandc.c b/drivers/mtd/nand/qcom_nandc.c index 09d5f7df6023..65d1be2c3049 100644 --- a/drivers/mtd/nand/qcom_nandc.c +++ b/drivers/mtd/nand/qcom_nandc.c @@ -2760,7 +2760,7 @@ static int qcom_nandc_remove(struct platform_device *pdev) struct qcom_nand_host *host; list_for_each_entry(host, &nandc->host_list, node) - nand_release(nand_to_mtd(&host->chip)); + nand_release(&host->chip); qcom_nandc_unalloc(nandc); diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c index fc9287af4614..2cfa54941395 100644 --- a/drivers/mtd/nand/r852.c +++ b/drivers/mtd/nand/r852.c @@ -656,7 +656,7 @@ static int r852_register_nand_device(struct r852_device *dev) dev->card_registred = 1; return 0; error3: - nand_release(mtd); + nand_release(dev->chip); error1: /* Force card redetect */ dev->card_detected = 0; @@ -675,7 +675,7 @@ static void r852_unregister_nand_device(struct r852_device *dev) return; device_remove_file(&mtd->dev, &dev_attr_media_type); - nand_release(mtd); + nand_release(dev->chip); r852_engine_disable(dev); dev->card_registred = 0; } diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c index 4c383eeec6f6..f60de68bfabc 100644 --- a/drivers/mtd/nand/s3c2410.c +++ b/drivers/mtd/nand/s3c2410.c @@ -784,7 +784,7 @@ static int s3c24xx_nand_remove(struct platform_device *pdev) for (mtdno = 0; mtdno < info->mtd_count; mtdno++, ptr++) { pr_debug("releasing mtd %d (%p)\n", mtdno, ptr); - nand_release(nand_to_mtd(&ptr->chip)); + nand_release(&ptr->chip); } } diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c index 43db80e5d994..f2ed03ee3035 100644 --- a/drivers/mtd/nand/sh_flctl.c +++ b/drivers/mtd/nand/sh_flctl.c @@ -1231,7 +1231,7 @@ static int flctl_remove(struct platform_device *pdev) struct sh_flctl *flctl = platform_get_drvdata(pdev); flctl_release_dma(flctl); - nand_release(nand_to_mtd(&flctl->chip)); + nand_release(&flctl->chip); pm_runtime_disable(&pdev->dev); return 0; diff --git a/drivers/mtd/nand/sharpsl.c b/drivers/mtd/nand/sharpsl.c index f59c455d9f51..6cfff0c81153 100644 --- a/drivers/mtd/nand/sharpsl.c +++ b/drivers/mtd/nand/sharpsl.c @@ -192,7 +192,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev) return 0; err_add: - nand_release(mtd); + nand_release(this); err_scan: iounmap(sharpsl->io); @@ -210,7 +210,7 @@ static int sharpsl_nand_remove(struct platform_device *pdev) struct sharpsl_nand *sharpsl = platform_get_drvdata(pdev); /* Release resources, unregister device */ - nand_release(nand_to_mtd(&sharpsl->chip)); + nand_release(&sharpsl->chip); iounmap(sharpsl->io); diff --git a/drivers/mtd/nand/socrates_nand.c b/drivers/mtd/nand/socrates_nand.c index 575997d0ef8a..f960f18ea3e2 100644 --- a/drivers/mtd/nand/socrates_nand.c +++ b/drivers/mtd/nand/socrates_nand.c @@ -195,7 +195,7 @@ static int socrates_nand_probe(struct platform_device *ofdev) if (!res) return res; - nand_release(mtd); + nand_release(nand_chip); out: iounmap(host->io_base); @@ -208,9 +208,8 @@ out: static int socrates_nand_remove(struct platform_device *ofdev) { struct socrates_nand_host *host = dev_get_drvdata(&ofdev->dev); - struct mtd_info *mtd = nand_to_mtd(&host->nand_chip); - nand_release(mtd); + nand_release(&host->nand_chip); iounmap(host->io_base); diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c index 8e5231482397..d6e31e8a7b66 100644 --- a/drivers/mtd/nand/sunxi_nand.c +++ b/drivers/mtd/nand/sunxi_nand.c @@ -2125,7 +2125,7 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc, ret = mtd_device_register(mtd, NULL, 0); if (ret) { dev_err(dev, "failed to register mtd device: %d\n", ret); - nand_release(mtd); + nand_release(nand); return ret; } @@ -2164,7 +2164,7 @@ static void sunxi_nand_chips_cleanup(struct sunxi_nfc *nfc) while (!list_empty(&nfc->chips)) { chip = list_first_entry(&nfc->chips, struct sunxi_nand_chip, node); - nand_release(nand_to_mtd(&chip->nand)); + nand_release(&chip->nand); sunxi_nand_ecc_cleanup(&chip->nand.ecc); list_del(&chip->node); } diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c index ce366816a7ef..1ab16a90ea29 100644 --- a/drivers/mtd/nand/tango_nand.c +++ b/drivers/mtd/nand/tango_nand.c @@ -619,7 +619,7 @@ static int tango_nand_remove(struct platform_device *pdev) for (cs = 0; cs < MAX_CS; ++cs) { if (nfc->chips[cs]) - nand_release(nand_to_mtd(&nfc->chips[cs]->nand_chip)); + nand_release(&nfc->chips[cs]->nand_chip); } return 0; diff --git a/drivers/mtd/nand/tmio_nand.c b/drivers/mtd/nand/tmio_nand.c index 84dbf32332e1..5a082d9432f9 100644 --- a/drivers/mtd/nand/tmio_nand.c +++ b/drivers/mtd/nand/tmio_nand.c @@ -448,7 +448,7 @@ static int tmio_probe(struct platform_device *dev) if (!retval) return retval; - nand_release(mtd); + nand_release(nand_chip); err_irq: tmio_hw_stop(dev, tmio); @@ -459,7 +459,7 @@ static int tmio_remove(struct platform_device *dev) { struct tmio_nand *tmio = platform_get_drvdata(dev); - nand_release(nand_to_mtd(&tmio->chip)); + nand_release(&tmio->chip); tmio_hw_stop(dev, tmio); return 0; } diff --git a/drivers/mtd/nand/txx9ndfmc.c b/drivers/mtd/nand/txx9ndfmc.c index b567d212fe7d..236181b2985a 100644 --- a/drivers/mtd/nand/txx9ndfmc.c +++ b/drivers/mtd/nand/txx9ndfmc.c @@ -390,7 +390,7 @@ static int __exit txx9ndfmc_remove(struct platform_device *dev) chip = mtd_to_nand(mtd); txx9_priv = nand_get_controller_data(chip); - nand_release(mtd); + nand_release(chip); kfree(txx9_priv->mtdname); kfree(txx9_priv); } diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c index e2583a539b41..688393526b5a 100644 --- a/drivers/mtd/nand/vf610_nfc.c +++ b/drivers/mtd/nand/vf610_nfc.c @@ -794,7 +794,7 @@ static int vf610_nfc_remove(struct platform_device *pdev) struct mtd_info *mtd = platform_get_drvdata(pdev); struct vf610_nfc *nfc = mtd_to_nfc(mtd); - nand_release(mtd); + nand_release(mtd_to_nand(mtd)); clk_disable_unprepare(nfc->clk); return 0; } diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c index 9926b4e3d69d..1988bb943d1b 100644 --- a/drivers/mtd/nand/xway_nand.c +++ b/drivers/mtd/nand/xway_nand.c @@ -211,7 +211,7 @@ static int xway_nand_probe(struct platform_device *pdev) err = mtd_device_register(mtd, NULL, 0); if (err) - nand_release(mtd); + nand_release(&data->chip); return err; } @@ -223,7 +223,7 @@ static int xway_nand_remove(struct platform_device *pdev) { struct xway_nand_data *data = platform_get_drvdata(pdev); - nand_release(nand_to_mtd(&data->chip)); + nand_release(&data->chip); return 0; } diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2b05f4273bab..e9a791f46eb6 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -22,6 +22,7 @@ #include #include +struct nand_chip; struct mtd_info; struct nand_flash_dev; struct device_node; @@ -37,7 +38,7 @@ int nand_scan_ident(struct mtd_info *mtd, int max_chips, int nand_scan_tail(struct mtd_info *mtd); /* Unregister the MTD device and free resources held by the NAND device */ -void nand_release(struct mtd_info *mtd); +void nand_release(struct nand_chip *chip); /* Internal helper for board drivers which need to override command function */ void nand_wait_ready(struct mtd_info *mtd); @@ -227,9 +228,6 @@ enum nand_ecc_algo { #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 -/* Keep gcc happy */ -struct nand_chip; - /* ONFI features */ #define ONFI_FEATURE_16_BIT_BUS (1 << 0) #define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) From f17b4d893075df8219d3b6ad06eb0bb478d27e0e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 14:59:45 +0200 Subject: [PATCH 141/162] mtd: rawnand: diskonchip: Fix the probe error path [ Upstream commit c5be12e45940f1aa1b5dfa04db5d15ad24f7c896 ] Not sure nand_cleanup() is the right function to call here but in any case it is not nand_release(). Indeed, even a comment says that calling nand_release() is a bit of a hack as there is no MTD device to unregister. So switch to nand_cleanup() for now and drop this comment. There is no Fixes tag applying here as the use of nand_release() in this driver predates by far the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible. However, pointing this commit as the culprit for backporting purposes makes sense even if it did not intruce any bug. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-13-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/diskonchip.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c index 12cac07f5cf2..4f48a9b4f9e3 100644 --- a/drivers/mtd/nand/diskonchip.c +++ b/drivers/mtd/nand/diskonchip.c @@ -1605,13 +1605,10 @@ static int __init doc_probe(unsigned long physadr) numchips = doc2001_init(mtd); if ((ret = nand_scan(mtd, numchips)) || (ret = doc->late_init(mtd))) { - /* DBB note: i believe nand_release is necessary here, as + /* DBB note: i believe nand_cleanup is necessary here, as buffers may have been allocated in nand_base. Check with Thomas. FIX ME! */ - /* nand_release will call mtd_device_unregister, but we - haven't yet added it. This is handled without incident by - mtd_device_unregister, as far as I can tell. */ - nand_release(nand); + nand_cleanup(nand); kfree(nand); goto fail; } From 213616adc47279ec22f830f23eb44b95619a6476 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:21 +0200 Subject: [PATCH 142/162] mtd: rawnand: sharpsl: Fix the probe error path [ Upstream commit 0f44b3275b3798ccb97a2f51ac85871c30d6fbbc ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. There is no Fixes tag applying here as the use of nand_release() in this driver predates by far the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible. However, pointing this commit as the culprit for backporting purposes makes sense. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-49-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/sharpsl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/sharpsl.c b/drivers/mtd/nand/sharpsl.c index 6cfff0c81153..c245d66609c1 100644 --- a/drivers/mtd/nand/sharpsl.c +++ b/drivers/mtd/nand/sharpsl.c @@ -192,7 +192,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev) return 0; err_add: - nand_release(this); + nand_cleanup(this); err_scan: iounmap(sharpsl->io); From 7a79fc16d903dc695cf326ce40717126e68ba9be Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:33 +0200 Subject: [PATCH 143/162] mtd: rawnand: xway: Fix the probe error path [ Upstream commit 34531be5e804a8e1abf314a6c3a19fe342e4a154 ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. There is no real Fixes tag applying here as the use of nand_release() in this driver predates the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible. However, pointing this commit as the culprit for backporting purposes makes sense even if this commit is not introducing any bug. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-61-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/xway_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c index 1988bb943d1b..176a94fa31d7 100644 --- a/drivers/mtd/nand/xway_nand.c +++ b/drivers/mtd/nand/xway_nand.c @@ -211,7 +211,7 @@ static int xway_nand_probe(struct platform_device *pdev) err = mtd_device_register(mtd, NULL, 0); if (err) - nand_release(&data->chip); + nand_cleanup(&data->chip); return err; } From c8d77944438efb7d24f69665d4a64ca9b9d660b0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:06 +0200 Subject: [PATCH 144/162] mtd: rawnand: orion: Fix the probe error path [ Upstream commit be238fbf78e4c7c586dac235ab967d3e565a4d1a ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. There is no real Fixes tag applying here as the use of nand_release() in this driver predates by far the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible. However, pointing this commit as the culprit for backporting purposes makes sense even if this commit is not introducing any bug. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-34-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/orion_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c index 2f21c678d6ef..df07f9b4cf03 100644 --- a/drivers/mtd/nand/orion_nand.c +++ b/drivers/mtd/nand/orion_nand.c @@ -186,7 +186,7 @@ static int __init orion_nand_probe(struct platform_device *pdev) mtd->name = "orion_nand"; ret = mtd_device_register(mtd, board->parts, board->nr_parts); if (ret) { - nand_release(nc); + nand_cleanup(nc); goto no_dev; } From 155b83bf8ce45c0a2229e0abc92358dc3bd03974 Mon Sep 17 00:00:00 2001 From: Nishka Dasgupta Date: Tue, 9 Jul 2019 22:40:16 +0530 Subject: [PATCH 145/162] mtd: rawnand: oxnas: Add of_node_put() [ Upstream commit c436f68beeb20f2f92937677db1d9069b0dd2a3d ] Each iteration of for_each_child_of_node puts the previous node, but in the case of a goto from the middle of the loop, there is no put, thus causing a memory leak. Hence add an of_node_put under a new goto to put the node at a loop exit. Issue found with Coccinelle. Signed-off-by: Nishka Dasgupta Signed-off-by: Miquel Raynal Signed-off-by: Sasha Levin --- drivers/mtd/nand/oxnas_nand.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/oxnas_nand.c b/drivers/mtd/nand/oxnas_nand.c index ff5899988738..7f0ba28f8a00 100644 --- a/drivers/mtd/nand/oxnas_nand.c +++ b/drivers/mtd/nand/oxnas_nand.c @@ -123,7 +123,7 @@ static int oxnas_nand_probe(struct platform_device *pdev) GFP_KERNEL); if (!chip) { err = -ENOMEM; - goto err_clk_unprepare; + goto err_release_child; } chip->controller = &oxnas->base; @@ -144,12 +144,12 @@ static int oxnas_nand_probe(struct platform_device *pdev) /* Scan to find existence of the device */ err = nand_scan(mtd, 1); if (err) - goto err_clk_unprepare; + goto err_release_child; err = mtd_device_register(mtd, NULL, 0); if (err) { nand_release(chip); - goto err_clk_unprepare; + goto err_release_child; } oxnas->chips[nchips] = chip; @@ -166,6 +166,8 @@ static int oxnas_nand_probe(struct platform_device *pdev) return 0; +err_release_child: + of_node_put(nand_np); err_clk_unprepare: clk_disable_unprepare(oxnas->clk); return err; From 17dcc86c57f019b5eb03941c66113a304eb48760 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:09 +0200 Subject: [PATCH 146/162] mtd: rawnand: oxnas: Fix the probe error path [ Upstream commit 154298e2a3f6c9ce1d76cdb48d89fd5b107ea1a3 ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. While at it, be consistent and move the function call in the error path thanks to a goto statement. Fixes: 668592492409 ("mtd: nand: Add OX820 NAND Support") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-37-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/oxnas_nand.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/oxnas_nand.c b/drivers/mtd/nand/oxnas_nand.c index 7f0ba28f8a00..350d4226b436 100644 --- a/drivers/mtd/nand/oxnas_nand.c +++ b/drivers/mtd/nand/oxnas_nand.c @@ -147,10 +147,8 @@ static int oxnas_nand_probe(struct platform_device *pdev) goto err_release_child; err = mtd_device_register(mtd, NULL, 0); - if (err) { - nand_release(chip); - goto err_release_child; - } + if (err) + goto err_cleanup_nand; oxnas->chips[nchips] = chip; ++nchips; @@ -166,6 +164,8 @@ static int oxnas_nand_probe(struct platform_device *pdev) return 0; +err_cleanup_nand: + nand_cleanup(chip); err_release_child: of_node_put(nand_np); err_clk_unprepare: From 540fb7bcbb21ef140b14e2bac1496fb1e64215b0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:23 +0200 Subject: [PATCH 147/162] mtd: rawnand: socrates: Fix the probe error path [ Upstream commit 9c6c2e5cc77119ce0dacb4f9feedb73ce0354421 ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. There is no real Fixes tag applying here as the use of nand_release() in this driver predates by far the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible. However, pointing this commit as the culprit for backporting purposes makes sense even if this commit is not introducing any bug. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-51-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/socrates_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/socrates_nand.c b/drivers/mtd/nand/socrates_nand.c index f960f18ea3e2..8d4f0cd7197d 100644 --- a/drivers/mtd/nand/socrates_nand.c +++ b/drivers/mtd/nand/socrates_nand.c @@ -195,7 +195,7 @@ static int socrates_nand_probe(struct platform_device *ofdev) if (!res) return res; - nand_release(nand_chip); + nand_cleanup(nand_chip); out: iounmap(host->io_base); From b61f085e2d8a0247c08ecce73b051462265a40d4 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:15 +0200 Subject: [PATCH 148/162] mtd: rawnand: plat_nand: Fix the probe error path [ Upstream commit 5284024b4dac5e94f7f374ca905c7580dbc455e9 ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. There is no real Fixes tag applying here as the use of nand_release() in this driver predates by far the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible, hence pointing it as the commit to fix for backporting purposes, even if this commit is not introducing any bug. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-43-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/plat_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c index 2906996d2262..8c2d1c5c9569 100644 --- a/drivers/mtd/nand/plat_nand.c +++ b/drivers/mtd/nand/plat_nand.c @@ -99,7 +99,7 @@ static int plat_nand_probe(struct platform_device *pdev) if (!err) return err; - nand_release(&data->chip); + nand_cleanup(&data->chip); out: if (pdata->ctrl.remove) pdata->ctrl.remove(pdev); From 90ac6e169c696c756b3ba0bb46105f995b9500bf Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:00 +0200 Subject: [PATCH 149/162] mtd: rawnand: mtk: Fix the probe error path [ Upstream commit 8a82bbcadec877f5f938c54026278dfc1f05a332 ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. There is no real Fixes tag applying here as the use of nand_release() in this driver predates the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible. However, pointing this commit as the culprit for backporting purposes makes sense even if this commit is not introducing any bug. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-28-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/mtk_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index 27fcce71ad38..ff314ce104e5 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -1357,7 +1357,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc, ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0); if (ret) { dev_err(dev, "mtd parse partition error\n"); - nand_release(nand); + nand_cleanup(nand); return ret; } From 214f9faf52a1ecdae2666157ef3d0b03ea33ced0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:29 +0200 Subject: [PATCH 150/162] mtd: rawnand: tmio: Fix the probe error path [ Upstream commit 75e9a330a9bd48f97a55a08000236084fe3dae56 ] nand_release() is supposed be called after MTD device registration. Here, only nand_scan() happened, so use nand_cleanup() instead. There is no real Fixes tag applying here as the use of nand_release() in this driver predates by far the introduction of nand_cleanup() in commit d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") which makes this change possible. However, pointing this commit as the culprit for backporting purposes makes sense even if this commit is not introducing any bug. Fixes: d44154f969a4 ("mtd: nand: Provide nand_cleanup() function to free NAND related resources") Signed-off-by: Miquel Raynal Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-57-miquel.raynal@bootlin.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/tmio_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/tmio_nand.c b/drivers/mtd/nand/tmio_nand.c index 5a082d9432f9..51f12b9f90ba 100644 --- a/drivers/mtd/nand/tmio_nand.c +++ b/drivers/mtd/nand/tmio_nand.c @@ -448,7 +448,7 @@ static int tmio_probe(struct platform_device *dev) if (!retval) return retval; - nand_release(nand_chip); + nand_cleanup(nand_chip); err_irq: tmio_hw_stop(dev, tmio); From 29b13c01407846c4b9846f3d6794f9fd84ce57c4 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 29 May 2020 14:54:43 +1000 Subject: [PATCH 151/162] crypto: algif_skcipher - Cap recv SG list at ctx->used commit 7cf81954705b7e5b057f7dc39a7ded54422ab6e1 upstream. Somewhere along the line the cap on the SG list length for receive was lost. This patch restores it and removes the subsequent test which is now redundant. Fixes: 2d97591ef43d ("crypto: af_alg - consolidation of...") Cc: Signed-off-by: Herbert Xu Reviewed-by: Stephan Mueller Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 90bc4e0f0785..1ce1284c9ed9 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -85,14 +85,10 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, return PTR_ERR(areq); /* convert iovecs of output buffers into RX SGL */ - err = af_alg_get_rsgl(sk, msg, flags, areq, -1, &len); + err = af_alg_get_rsgl(sk, msg, flags, areq, ctx->used, &len); if (err) goto free; - /* Process only as much RX buffers for which we have TX data */ - if (len > ctx->used) - len = ctx->used; - /* * If more buffers are to be expected to be processed, process only * full block size buffers. From b1c6e158566a6a5fc14eda605f1eb81bdf3f0e88 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 4 Jun 2020 11:52:53 -0700 Subject: [PATCH 152/162] crypto: algboss - don't wait during notifier callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 77251e41f89a813b4090f5199442f217bbf11297 upstream. When a crypto template needs to be instantiated, CRYPTO_MSG_ALG_REQUEST is sent to crypto_chain. cryptomgr_schedule_probe() handles this by starting a thread to instantiate the template, then waiting for this thread to complete via crypto_larval::completion. This can deadlock because instantiating the template may require loading modules, and this (apparently depending on userspace) may need to wait for the crc-t10dif module (lib/crc-t10dif.c) to be loaded. But crc-t10dif's module_init function uses crypto_register_notifier() and therefore takes crypto_chain.rwsem for write. That can't proceed until the notifier callback has finished, as it holds this semaphore for read. Fix this by removing the wait on crypto_larval::completion from within cryptomgr_schedule_probe(). It's actually unnecessary because crypto_alg_mod_lookup() calls crypto_larval_wait() itself after sending CRYPTO_MSG_ALG_REQUEST. This only actually became a problem in v4.20 due to commit b76377543b73 ("crc-t10dif: Pick better transform if one becomes available"), but the unnecessary wait was much older. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=207159 Reported-by: Mike Gerow Fixes: 398710379f51 ("crypto: algapi - Move larval completion into algboss") Cc: # v3.6+ Cc: Martin K. Petersen Signed-off-by: Eric Biggers Reported-by: Kai Lüke Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algboss.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/crypto/algboss.c b/crypto/algboss.c index 960d8548171b..9d253e1016b1 100644 --- a/crypto/algboss.c +++ b/crypto/algboss.c @@ -194,8 +194,6 @@ static int cryptomgr_schedule_probe(struct crypto_larval *larval) if (IS_ERR(thread)) goto err_put_larval; - wait_for_completion_interruptible(&larval->completion); - return NOTIFY_STOP; err_put_larval: From c18d5164ff8a81bee55242867e91ac83a2286afa Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 12 May 2020 17:02:56 +0900 Subject: [PATCH 153/162] kprobes: Fix to protect kick_kprobe_optimizer() by kprobe_mutex commit 1a0aa991a6274161c95a844c58cfb801d681eb59 upstream. In kprobe_optimizer() kick_kprobe_optimizer() is called without kprobe_mutex, but this can race with other caller which is protected by kprobe_mutex. To fix that, expand kprobe_mutex protected area to protect kick_kprobe_optimizer() call. Link: http://lkml.kernel.org/r/158927057586.27680.5036330063955940456.stgit@devnote2 Fixes: cd7ebe2298ff ("kprobes: Use text_poke_smp_batch for optimizing") Cc: Ingo Molnar Cc: "Gustavo A . R . Silva" Cc: Anders Roxell Cc: "Naveen N . Rao" Cc: Anil S Keshavamurthy Cc: David Miller Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Ziqian SUN Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- kernel/kprobes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 66f1818d4762..484670370a6a 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -599,11 +599,12 @@ static void kprobe_optimizer(struct work_struct *work) mutex_unlock(&module_mutex); mutex_unlock(&text_mutex); cpus_read_unlock(); - mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); + + mutex_unlock(&kprobe_mutex); } /* Wait for completing optimization and unoptimization */ From 8a7737dd007b354caf73bfb4ae54b8966cdb0695 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Fri, 22 May 2020 01:59:00 +0800 Subject: [PATCH 154/162] e1000e: Do not wake up the system via WOL if device wakeup is disabled commit 6bf6be1127f7e6d4bf39f84d56854e944d045d74 upstream. Currently the system will be woken up via WOL(Wake On LAN) even if the device wakeup ability has been disabled via sysfs: cat /sys/devices/pci0000:00/0000:00:1f.6/power/wakeup disabled The system should not be woken up if the user has explicitly disabled the wake up ability for this device. This patch clears the WOL ability of this network device if the user has disabled the wake up ability in sysfs. Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver") Reported-by: "Rafael J. Wysocki" Reviewed-by: Andy Shevchenko Cc: Signed-off-by: Chen Yu Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/e1000e/netdev.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 5269af303f55..fff55f0bed30 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6328,11 +6328,17 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 ctrl, ctrl_ext, rctl, status; - /* Runtime suspend should only enable wakeup for link changes */ - u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; + u32 ctrl, ctrl_ext, rctl, status, wufc; int retval = 0; + /* Runtime suspend should only enable wakeup for link changes */ + if (runtime) + wufc = E1000_WUFC_LNKC; + else if (device_may_wakeup(&pdev->dev)) + wufc = adapter->wol; + else + wufc = 0; + status = er32(STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -6389,7 +6395,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); } else if (hw->mac.type >= e1000_pch_lpt) { - if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) + if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) /* ULP does not support wake from unicast, multicast * or broadcast. */ From 62ce8f40b372755cea64291a5657aed702c6068b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 12 May 2020 17:03:18 +0900 Subject: [PATCH 155/162] kretprobe: Prevent triggering kretprobe from within kprobe_flush_task [ Upstream commit 9b38cc704e844e41d9cf74e647bff1d249512cb3 ] Ziqian reported lockup when adding retprobe on _raw_spin_lock_irqsave. My test was also able to trigger lockdep output: ============================================ WARNING: possible recursive locking detected 5.6.0-rc6+ #6 Not tainted -------------------------------------------- sched-messaging/2767 is trying to acquire lock: ffffffff9a492798 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_hash_lock+0x52/0xa0 but task is already holding lock: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(kretprobe_table_locks[i].lock)); lock(&(kretprobe_table_locks[i].lock)); *** DEADLOCK *** May be due to missing lock nesting notation 1 lock held by sched-messaging/2767: #0: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 stack backtrace: CPU: 3 PID: 2767 Comm: sched-messaging Not tainted 5.6.0-rc6+ #6 Call Trace: dump_stack+0x96/0xe0 __lock_acquire.cold.57+0x173/0x2b7 ? native_queued_spin_lock_slowpath+0x42b/0x9e0 ? lockdep_hardirqs_on+0x590/0x590 ? __lock_acquire+0xf63/0x4030 lock_acquire+0x15a/0x3d0 ? kretprobe_hash_lock+0x52/0xa0 _raw_spin_lock_irqsave+0x36/0x70 ? kretprobe_hash_lock+0x52/0xa0 kretprobe_hash_lock+0x52/0xa0 trampoline_handler+0xf8/0x940 ? kprobe_fault_handler+0x380/0x380 ? find_held_lock+0x3a/0x1c0 kretprobe_trampoline+0x25/0x50 ? lock_acquired+0x392/0xbc0 ? _raw_spin_lock_irqsave+0x50/0x70 ? __get_valid_kprobe+0x1f0/0x1f0 ? _raw_spin_unlock_irqrestore+0x3b/0x40 ? finish_task_switch+0x4b9/0x6d0 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 The code within the kretprobe handler checks for probe reentrancy, so we won't trigger any _raw_spin_lock_irqsave probe in there. The problem is in outside kprobe_flush_task, where we call: kprobe_flush_task kretprobe_table_lock raw_spin_lock_irqsave _raw_spin_lock_irqsave where _raw_spin_lock_irqsave triggers the kretprobe and installs kretprobe_trampoline handler on _raw_spin_lock_irqsave return. The kretprobe_trampoline handler is then executed with already locked kretprobe_table_locks, and first thing it does is to lock kretprobe_table_locks ;-) the whole lockup path like: kprobe_flush_task kretprobe_table_lock raw_spin_lock_irqsave _raw_spin_lock_irqsave ---> probe triggered, kretprobe_trampoline installed ---> kretprobe_table_locks locked kretprobe_trampoline trampoline_handler kretprobe_hash_lock(current, &head, &flags); <--- deadlock Adding kprobe_busy_begin/end helpers that mark code with fake probe installed to prevent triggering of another kprobe within this code. Using these helpers in kprobe_flush_task, so the probe recursion protection check is hit and the probe is never set to prevent above lockup. Link: http://lkml.kernel.org/r/158927059835.27680.7011202830041561604.stgit@devnote2 Fixes: ef53d9c5e4da ("kprobes: improve kretprobe scalability with hashed locking") Cc: Ingo Molnar Cc: "Gustavo A . R . Silva" Cc: Anders Roxell Cc: "Naveen N . Rao" Cc: Anil S Keshavamurthy Cc: David Miller Cc: Ingo Molnar Cc: Peter Zijlstra Cc: stable@vger.kernel.org Reported-by: "Ziqian SUN (Zamir)" Acked-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Sasha Levin --- arch/x86/kernel/kprobes/core.c | 16 +++------------- include/linux/kprobes.h | 4 ++++ kernel/kprobes.c | 24 ++++++++++++++++++++++++ 3 files changed, 31 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 9d7bb8de2917..02665ffef050 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -744,16 +744,11 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); -static struct kprobe kretprobe_kprobe = { - .addr = (void *)kretprobe_trampoline, -}; - /* * Called from kretprobe_trampoline */ __visible __used void *trampoline_handler(struct pt_regs *regs) { - struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -763,16 +758,12 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; - preempt_disable(); - /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never run in kprobe handler, kprobe must not * be running at this point. */ - kcb = get_kprobe_ctlblk(); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + kprobe_busy_begin(); INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -851,7 +842,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); + __this_cpu_write(current_kprobe, &kprobe_busy); } recycle_rp_inst(ri, &empty_rp); @@ -867,8 +858,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - __this_cpu_write(current_kprobe, NULL); - preempt_enable(); + kprobe_busy_end(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 520702b82134..be7a49f437ea 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -385,6 +385,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) return this_cpu_ptr(&kprobe_ctlblk); } +extern struct kprobe kprobe_busy; +void kprobe_busy_begin(void); +void kprobe_busy_end(void); + kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 484670370a6a..f2d2194b51ca 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1218,6 +1218,26 @@ __releases(hlist_lock) } NOKPROBE_SYMBOL(kretprobe_table_unlock); +struct kprobe kprobe_busy = { + .addr = (void *) get_kprobe, +}; + +void kprobe_busy_begin(void) +{ + struct kprobe_ctlblk *kcb; + + preempt_disable(); + __this_cpu_write(current_kprobe, &kprobe_busy); + kcb = get_kprobe_ctlblk(); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; +} + +void kprobe_busy_end(void) +{ + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); +} + /* * This function is called from finish_task_switch when task tk becomes dead, * so that we can recycle any function-return probe instances associated @@ -1235,6 +1255,8 @@ void kprobe_flush_task(struct task_struct *tk) /* Early boot. kretprobe_table_locks not yet initialized. */ return; + kprobe_busy_begin(); + INIT_HLIST_HEAD(&empty_rp); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; @@ -1248,6 +1270,8 @@ void kprobe_flush_task(struct task_struct *tk) hlist_del(&ri->hlist); kfree(ri); } + + kprobe_busy_end(); } NOKPROBE_SYMBOL(kprobe_flush_task); From 1714d977f52fd6199b1ae0e9c6afb551a7538c02 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Oct 2019 21:18:08 +0200 Subject: [PATCH 156/162] sched/rt, net: Use CONFIG_PREEMPTION.patch [ Upstream commit 2da2b32fd9346009e9acdb68c570ca8d3966aba7 ] CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Update the comment to use CONFIG_PREEMPTION. Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: David S. Miller Cc: Linus Torvalds Cc: Peter Zijlstra Cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/20191015191821.11479-22-bigeasy@linutronix.de Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index ed552ad3f783..9e4a00462f5c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -901,7 +901,7 @@ EXPORT_SYMBOL(dev_get_by_napi_id); * * The use of raw_seqcount_begin() and cond_resched() before * retrying is required as we want to give the writers a chance - * to complete when CONFIG_PREEMPT is not set. + * to complete when CONFIG_PREEMPTION is not set. */ int netdev_get_name(struct net *net, char *name, int ifindex) { From 7569bfabdca657dbc84d3f1c34ffd9c91ee85d0c Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Wed, 3 Jun 2020 16:49:44 +0200 Subject: [PATCH 157/162] net: core: device_rename: Use rwsem instead of a seqcount [ Upstream commit 11d6011c2cf29f7c8181ebde6c8bc0c4d83adcd7 ] Sequence counters write paths are critical sections that must never be preempted, and blocking, even for CONFIG_PREEMPTION=n, is not allowed. Commit 5dbe7c178d3f ("net: fix kernel deadlock with interface rename and netdev name retrieval.") handled a deadlock, observed with CONFIG_PREEMPTION=n, where the devnet_rename seqcount read side was infinitely spinning: it got scheduled after the seqcount write side blocked inside its own critical section. To fix that deadlock, among other issues, the commit added a cond_resched() inside the read side section. While this will get the non-preemptible kernel eventually unstuck, the seqcount reader is fully exhausting its slice just spinning -- until TIF_NEED_RESCHED is set. The fix is also still broken: if the seqcount reader belongs to a real-time scheduling policy, it can spin forever and the kernel will livelock. Disabling preemption over the seqcount write side critical section will not work: inside it are a number of GFP_KERNEL allocations and mutex locking through the drivers/base/ :: device_rename() call chain. >From all the above, replace the seqcount with a rwsem. Fixes: 5dbe7c178d3f (net: fix kernel deadlock with interface rename and netdev name retrieval.) Fixes: 30e6c9fa93cf (net: devnet_rename_seq should be a seqcount) Fixes: c91f6df2db49 (sockopt: Change getsockopt() of SO_BINDTODEVICE to return an interface name) Cc: Reported-by: kbuild test robot [ v1 missing up_read() on error exit ] Reported-by: Dan Carpenter [ v1 missing up_read() on error exit ] Signed-off-by: Ahmed S. Darwish Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/dev.c | 40 ++++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 22 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 9e4a00462f5c..0aaa1426450f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -83,6 +83,7 @@ #include #include #include +#include #include #include #include @@ -194,7 +195,7 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); -static seqcount_t devnet_rename_seq; +static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { @@ -898,33 +899,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id); * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. - * - * The use of raw_seqcount_begin() and cond_resched() before - * retrying is required as we want to give the writers a chance - * to complete when CONFIG_PREEMPTION is not set. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; - unsigned int seq; + int ret; -retry: - seq = raw_seqcount_begin(&devnet_rename_seq); + down_read(&devnet_rename_sem); rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { - rcu_read_unlock(); - return -ENODEV; + ret = -ENODEV; + goto out; } strcpy(name, dev->name); - rcu_read_unlock(); - if (read_seqcount_retry(&devnet_rename_seq, seq)) { - cond_resched(); - goto retry; - } - return 0; + ret = 0; +out: + rcu_read_unlock(); + up_read(&devnet_rename_sem); + return ret; } /** @@ -1189,10 +1185,10 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return 0; } @@ -1200,7 +1196,7 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); if (err < 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return err; } @@ -1215,11 +1211,11 @@ rollback: if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); dev->name_assign_type = old_assign_type; - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return ret; } - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); netdev_adjacent_rename_links(dev, oldname); @@ -1240,7 +1236,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); dev->name_assign_type = old_assign_type; From 0bd807d5638fff7c50c08e6dabe72e2ba65f8e2b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 Sep 2019 16:52:29 +1000 Subject: [PATCH 158/162] md: add feature flag MD_FEATURE_RAID0_LAYOUT [ Upstream commit 33f2c35a54dfd75ad0e7e86918dcbe4de799a56c ] Due to a bug introduced in Linux 3.14 we cannot determine the correctly layout for a multi-zone RAID0 array - there are two possibilities. It is possible to tell the kernel which to chose using a module parameter, but this can be clumsy to use. It would be best if the choice were recorded in the metadata. So add a feature flag for this purpose. If it is set, then the 'layout' field of the superblock is used to determine which layout to use. If this flag is not set, then mddev->layout gets set to -1, which causes the module parameter to be required. Acked-by: Guoqing Jiang Signed-off-by: NeilBrown Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/md.c | 13 +++++++++++++ drivers/md/raid0.c | 3 +++ include/uapi/linux/raid/md_p.h | 2 ++ 3 files changed, 18 insertions(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 948344531baf..702a7d2c7e1e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1168,6 +1168,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->new_layout = mddev->layout; mddev->new_chunk_sectors = mddev->chunk_sectors; } + if (mddev->level == 0) + mddev->layout = -1; if (sb->state & (1<recovery_cp = MaxSector; @@ -1584,6 +1586,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset; } + if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) && + sb->level != 0) + return -EINVAL; + if (!refdev) { ret = 1; } else { @@ -1694,6 +1700,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->new_chunk_sectors = mddev->chunk_sectors; } + if (mddev->level == 0 && + !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT)) + mddev->layout = -1; + if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) set_bit(MD_HAS_JOURNAL, &mddev->flags); @@ -6757,6 +6767,9 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->external = 0; mddev->layout = info->layout; + if (mddev->level == 0) + /* Cannot trust RAID0 layout info here */ + mddev->layout = -1; mddev->chunk_sectors = info->chunk_size >> 9; if (mddev->persistent) { diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index cdafa5e0ea6d..e179c121c030 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -152,6 +152,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) if (conf->nr_strip_zones == 1) { conf->layout = RAID0_ORIG_LAYOUT; + } else if (mddev->layout == RAID0_ORIG_LAYOUT || + mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = mddev->layout; } else if (default_layout == RAID0_ORIG_LAYOUT || default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { conf->layout = default_layout; diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index b0d15c73f6d7..1f2d8c81f0e0 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -329,6 +329,7 @@ struct mdp_superblock_1 { #define MD_FEATURE_JOURNAL 512 /* support write cache */ #define MD_FEATURE_PPL 1024 /* support PPL */ #define MD_FEATURE_MULTIPLE_PPLS 2048 /* support for multiple PPLs */ +#define MD_FEATURE_RAID0_LAYOUT 4096 /* layout is meaningful for RAID0 */ #define MD_FEATURE_ALL (MD_FEATURE_BITMAP_OFFSET \ |MD_FEATURE_RECOVERY_OFFSET \ |MD_FEATURE_RESHAPE_ACTIVE \ @@ -341,6 +342,7 @@ struct mdp_superblock_1 { |MD_FEATURE_JOURNAL \ |MD_FEATURE_PPL \ |MD_FEATURE_MULTIPLE_PPLS \ + |MD_FEATURE_RAID0_LAYOUT \ ) struct r5l_payload_header { From f4fd2eacafb5dcbdb6757d1f3e3bd0fee7482efe Mon Sep 17 00:00:00 2001 From: Kai Huang Date: Fri, 3 May 2019 03:08:52 -0700 Subject: [PATCH 159/162] kvm: x86: Move kvm_set_mmio_spte_mask() from x86.c to mmu.c [ Upstream commit 7b6f8a06e482960ba6ab06faba51c8f3727a5c7b ] As a prerequisite to fix several SPTE reserved bits related calculation errors caused by MKTME, which requires kvm_set_mmio_spte_mask() to use local static variable defined in mmu.c. Also move call site of kvm_set_mmio_spte_mask() from kvm_arch_init() to kvm_mmu_module_init() so that kvm_set_mmio_spte_mask() can be static. Reviewed-by: Sean Christopherson Signed-off-by: Kai Huang Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- arch/x86/kvm/mmu.c | 31 +++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 31 ------------------------------- 2 files changed, 31 insertions(+), 31 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7220ab210dcf..b71277405ae1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5675,6 +5675,35 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) return 0; } +static void kvm_set_mmio_spte_mask(void) +{ + u64 mask; + int maxphyaddr = boot_cpu_data.x86_phys_bits; + + /* + * Set the reserved bits and the present bit of an paging-structure + * entry to generate page fault with PFER.RSV = 1. + */ + + /* + * Mask the uppermost physical address bit, which would be reserved as + * long as the supported physical address width is less than 52. + */ + mask = 1ull << 51; + + /* Set the present bit. */ + mask |= 1ull; + + /* + * If reserved bit is not supported, clear the present bit to disable + * mmio page fault. + */ + if (maxphyaddr == 52) + mask &= ~1ull; + + kvm_mmu_set_mmio_spte_mask(mask, mask); +} + int kvm_mmu_module_init(void) { if (nx_huge_pages == -1) @@ -5682,6 +5711,8 @@ int kvm_mmu_module_init(void) kvm_mmu_reset_all_pte_masks(); + kvm_set_mmio_spte_mask(); + pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, SLAB_ACCOUNT, NULL); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1477e23827c2..3401061a2231 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6291,35 +6291,6 @@ void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); -static void kvm_set_mmio_spte_mask(void) -{ - u64 mask; - int maxphyaddr = boot_cpu_data.x86_phys_bits; - - /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. - */ - - /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. - */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (maxphyaddr == 52) - mask &= ~1ull; - - kvm_mmu_set_mmio_spte_mask(mask, mask); -} - #ifdef CONFIG_X86_64 static void pvclock_gtod_update_fn(struct work_struct *work) { @@ -6397,8 +6368,6 @@ int kvm_arch_init(void *opaque) if (r) goto out_free_percpu; - kvm_set_mmio_spte_mask(); - kvm_x86_ops = ops; kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, From 30870f278e76ef8781dfc0ff8d9a9f3b2becc8cc Mon Sep 17 00:00:00 2001 From: Kai Huang Date: Fri, 3 May 2019 03:08:53 -0700 Subject: [PATCH 160/162] kvm: x86: Fix reserved bits related calculation errors caused by MKTME [ Upstream commit f3ecb59dd49f1742b97df6ba071aaa3d031154ac ] Intel MKTME repurposes several high bits of physical address as 'keyID' for memory encryption thus effectively reduces platform's maximum physical address bits. Exactly how many bits are reduced is configured by BIOS. To honor such HW behavior, the repurposed bits are reduced from cpuinfo_x86->x86_phys_bits when MKTME is detected in CPU detection. Similarly, AMD SME/SEV also reduces physical address bits for memory encryption, and cpuinfo->x86_phys_bits is reduced too when SME/SEV is detected, so for both MKTME and SME/SEV, boot_cpu_data.x86_phys_bits doesn't hold physical address bits reported by CPUID anymore. Currently KVM treats bits from boot_cpu_data.x86_phys_bits to 51 as reserved bits, but it's not true anymore for MKTME, since MKTME treats those reduced bits as 'keyID', but not reserved bits. Therefore boot_cpu_data.x86_phys_bits cannot be used to calculate reserved bits anymore, although we can still use it for AMD SME/SEV since SME/SEV treats the reduced bits differently -- they are treated as reserved bits, the same as other reserved bits in page table entity [1]. Fix by introducing a new 'shadow_phys_bits' variable in KVM x86 MMU code to store the effective physical bits w/o reserved bits -- for MKTME, it equals to physical address reported by CPUID, and for SME/SEV, it is boot_cpu_data.x86_phys_bits. Note that for the physical address bits reported to guest should remain unchanged -- KVM should report physical address reported by CPUID to guest, but not boot_cpu_data.x86_phys_bits. Because for Intel MKTME, there's no harm if guest sets up 'keyID' bits in guest page table (since MKTME only works at physical address level), and KVM doesn't even expose MKTME to guest. Arguably, for AMD SME/SEV, guest is aware of SEV thus it should adjust boot_cpu_data.x86_phys_bits when it detects SEV, therefore KVM should still reports physcial address reported by CPUID to guest. Reviewed-by: Sean Christopherson Signed-off-by: Kai Huang Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- arch/x86/kvm/mmu.c | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b71277405ae1..93640057f61b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -263,6 +263,11 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; */ static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +static u8 __read_mostly shadow_phys_bits; static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); @@ -445,6 +450,21 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); +static u8 kvm_get_shadow_phys_bits(void) +{ + /* + * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected + * in CPU detection code, but MKTME treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore for MKTME + * we should still return physical address bits reported by CPUID. + */ + if (!boot_cpu_has(X86_FEATURE_TME) || + WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008)) + return boot_cpu_data.x86_phys_bits; + + return cpuid_eax(0x80000008) & 0xff; +} + static void kvm_mmu_reset_all_pte_masks(void) { u8 low_phys_bits; @@ -458,6 +478,8 @@ static void kvm_mmu_reset_all_pte_masks(void) shadow_present_mask = 0; shadow_acc_track_mask = 0; + shadow_phys_bits = kvm_get_shadow_phys_bits(); + /* * If the CPU has 46 or less physical address bits, then set an * appropriate mask to guard against L1TF attacks. Otherwise, it is @@ -4314,7 +4336,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) */ shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), true); @@ -4351,13 +4373,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, false); if (!shadow_me_mask) @@ -4378,7 +4400,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - boot_cpu_data.x86_phys_bits, execonly); + shadow_phys_bits, execonly); } #define BYTE_MASK(access) \ @@ -5678,7 +5700,6 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) static void kvm_set_mmio_spte_mask(void) { u64 mask; - int maxphyaddr = boot_cpu_data.x86_phys_bits; /* * Set the reserved bits and the present bit of an paging-structure @@ -5698,7 +5719,7 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (maxphyaddr == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; kvm_mmu_set_mmio_spte_mask(mask, mask); From bcb5e31223420d1ef31f163b2ccd4ef513421586 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 27 May 2020 01:49:09 -0700 Subject: [PATCH 161/162] KVM: x86/mmu: Set mmio_value to '0' if reserved #PF can't be generated [ Upstream commit 6129ed877d409037b79866327102c9dc59a302fe ] Set the mmio_value to '0' instead of simply clearing the present bit to squash a benign warning in kvm_mmu_set_mmio_spte_mask() that complains about the mmio_value overlapping the lower GFN mask on systems with 52 bits of PA space. Opportunistically clean up the code and comments. Cc: stable@vger.kernel.org Fixes: d43e2675e96fc ("KVM: x86: only do L1TF workaround on affected processors") Signed-off-by: Sean Christopherson Message-Id: <20200527084909.23492-1-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- arch/x86/kvm/mmu.c | 27 +++++++++------------------ 1 file changed, 9 insertions(+), 18 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 93640057f61b..082d0cea72f4 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5702,25 +5702,16 @@ static void kvm_set_mmio_spte_mask(void) u64 mask; /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. + * Set a reserved PA bit in MMIO SPTEs to generate page faults with + * PFEC.RSVD=1 on MMIO accesses. 64-bit PTEs (PAE, x86-64, and EPT + * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports + * 52-bit physical addresses then there are no reserved PA bits in the + * PTEs and so the reserved PA approach must be disabled. */ - - /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. - */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (shadow_phys_bits == 52) - mask &= ~1ull; + if (shadow_phys_bits < 52) + mask = BIT_ULL(51) | PT_PRESENT_MASK; + else + mask = 0; kvm_mmu_set_mmio_spte_mask(mask, mask); } From f49027cf4ff06c384e4e16a8d45dc77bf6af3577 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 25 Jun 2020 15:42:02 +0200 Subject: [PATCH 162/162] Linux 4.14.186 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 04d63a6b4f46..5152fefccab5 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 185 +SUBLEVEL = 186 EXTRAVERSION = NAME = Petit Gorille